{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:42:19Z","timestamp":1781797339498,"version":"3.54.5"},"reference-count":239,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T00:00:00Z","timestamp":1655856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T00:00:00Z","timestamp":1655856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573330"],"award-info":[{"award-number":["61573330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61720106009"],"award-info":[{"award-number":["61720106009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s10462-022-10213-5","type":"journal-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T07:03:56Z","timestamp":1655881436000},"page":"1905-1969","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":347,"title":["A review of convolutional neural network architectures and their optimizations"],"prefix":"10.1007","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8101-0128","authenticated-orcid":false,"given":"Shuang","family":"Cong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,22]]},"reference":[{"key":"10213_CR1","doi-asserted-by":"crossref","unstructured":"Aghli N, Ribeiro E (2021) Combining weight pruning and knowledge distillation for CN compression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3191\u20133198","DOI":"10.1109\/CVPRW53098.2021.00356"},{"issue":"3","key":"10213_CR2","doi-asserted-by":"publisher","first-page":"445","DOI":"10.3390\/electronics9030445","volume":"9","author":"L Alzubaidi","year":"2020","unstructured":"Alzubaidi L, Al-Shamma O, Fadhel MA, Farhan L, Zhang J, Duan Y (2020) Optimizing the performance of breast cancer classification by employing the same domain transfer learning from hybrid deep convolutional neural network model. Electronics 9(3):445","journal-title":"Electronics"},{"issue":"1","key":"10213_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","volume":"8","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamar\u00eda J, Fadhel MA, Al-Amidie M, Farhan L (2021) Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8(1):1\u201374","journal-title":"Journal of big Data"},{"key":"10213_CR4","doi-asserted-by":"crossref","unstructured":"Alzubaidi L, Al-Shamma O, Fadhel MA, Farhan L, Zhang J (2018) Classification of red blood cells in sickle cell anemia using deep convolutional neural network. In: International conference on intelligent systems design and applications. Springer, Cham, pp 550\u2013559","DOI":"10.1007\/978-3-030-16657-1_51"},{"issue":"3","key":"10213_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3005348","volume":"13","author":"S Anwar","year":"2017","unstructured":"Anwar S, Hwang K, Sung W (2017) Structured pruning of deep convolutional neural networks. ACM J Emerg Technol Comput Syst JETC) 13(3):1\u201318","journal-title":"ACM Journal on Emerging Technologies in Computing Systems (JETC)"},{"key":"10213_CR6","doi-asserted-by":"crossref","unstructured":"Astrid M, Lee S-I (2017) Cp-decomposition with tensor power method for convolutional neural networks compression. In: 2017 IEEE  international conference on Big Data and Smart Computing (BigComp). IEEE, pp 115\u2013118","DOI":"10.1109\/BIGCOMP.2017.7881725"},{"key":"10213_CR7","first-page":"2654","volume":"3","author":"LJ Ba","year":"2013","unstructured":"Ba LJ, Caruana R (2013) Do deep nets really need to be deep? Adv Neural Inf Process Syst 3:2654\u20132662","journal-title":"Advances in neural information processing systems"},{"key":"10213_CR8","doi-asserted-by":"crossref","unstructured":"Bengio Y (2013) Deep learning of representations: Looking forward. In: International conference on statistical language and speech processing. Springer, Berlin, pp 1\u201337","DOI":"10.1007\/978-3-642-39593-2_1"},{"key":"10213_CR9","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint. arXiv:2004.10934"},{"key":"10213_CR10","doi-asserted-by":"crossref","unstructured":"Bucilu C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 535\u2013541","DOI":"10.1145\/1150402.1150464"},{"key":"10213_CR11","unstructured":"Chen X, Hsieh C-J (2020) Stabilizing differentiable architecture search via perturbation-based regularization. In: International conference on machine learning (PMLR), pp 1554\u20131565"},{"key":"10213_CR17","unstructured":"Chen T, Goodfellow I, Shlens J (2015a) Net2net: Accelerating learning via knowledge transfer. Computer Science"},{"key":"10213_CR18","unstructured":"Chen W, Wilson J, Tyree S, Weinberger K, Chen Y (2015b) Compressing neural networks with the hashing trick. In: International conference on machine learning (PMLR), pp 2285\u20132294"},{"key":"10213_CR13","doi-asserted-by":"crossref","unstructured":"Chen X, Li Z, Yuan Y, Yu G, Shen J, Qi D (2020) State-aware tracker for real-time video object segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision and pattern recognition, pp 9384\u20139393","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"10213_CR12","doi-asserted-by":"crossref","unstructured":"Chen B, Li P, Li B, Lin C, Li C, Sun M, Yan  J, Ouyang W (2021a) BN-NAS: neural architecture search with batch normalization. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 307\u2013316","DOI":"10.1109\/ICCV48922.2021.00037"},{"key":"10213_CR14","doi-asserted-by":"crossref","unstructured":"Chen M, Peng H, Fu J, Ling H (2021b) Autoformer: searching transformers for visual recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 12270\u201312280","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"10213_CR15","doi-asserted-by":"crossref","unstructured":"Chen Y, Dai X, Chen D, Liu M, Dong X, Yuan L, Liu Z (2021c) Mobile-former: bridging mobilenet and transformer. arXiv preprint. arXiv:2108.05895","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"10213_CR16","doi-asserted-by":"crossref","unstructured":"Cheng A-C, Lin CH, Juan D-C, Wei W, Sun M (2020) InstaNAS: instance-aware neural architecture search. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 3577\u20133584","DOI":"10.1609\/aaai.v34i04.5764"},{"key":"10213_CR19","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"issue":"7","key":"10213_CR20","doi-asserted-by":"publisher","first-page":"5113","DOI":"10.1007\/s10462-020-09816-7","volume":"53","author":"T Choudhary","year":"2020","unstructured":"Choudhary T, Mishra V, Goswami A, Sarangapani J (2020) A comprehensive survey on model compression and acceleration. Artif Intell Rev 53(7):5113\u20135155","journal-title":"Artificial Intelligence Review"},{"key":"10213_CR21","doi-asserted-by":"crossref","unstructured":"Chu X, Zhou T, Zhang B, Li J (2020a) Fair DARTS: eliminating unfair advantages in differentiable architecture search. In: European conference on computer vision. Springer, Munich, pp 465\u2013480","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"10213_CR22","doi-asserted-by":"crossref","unstructured":"Chu X, Zhang B, Xu R (2020b) Multi-objective reinforced evolution in mobile neural architecture search. In: European European conference on computer vision. Springer, Munich, pp 99\u2013113","DOI":"10.1007\/978-3-030-66823-5_6"},{"key":"10213_CR23","unstructured":"Clevert D-A, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (ELUS). arXiv preprint. arXiv:1511.07289"},{"key":"10213_CR24","doi-asserted-by":"crossref","unstructured":"Costa-Pazo A, Bhattacharjee S, Vazquez-Fernandez E, Marcel S (2016) The replay-mobile face presentation-attack database. In: International conference of the Biometrics Special Interest Group (BIOSIG). IEEE, pp 1\u20137","DOI":"10.1109\/BIOSIG.2016.7736936"},{"key":"10213_CR25","unstructured":"Courbariaux M, Bengio Y, David J-P (2015) BinaryConnect: training deep neural networks with binary weights during propagations. In: Advances in neural information processing systems, pp 3123\u20133131"},{"key":"10213_CR26","unstructured":"Courbariaux M, Hubara I, Soudry D, El-Yaniv R, Bengio Y (2016) Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or \u22121. arXiv preprint. arXiv:1602.02830"},{"key":"10213_CR27","unstructured":"Cs\u00e1ji BC et al (2001) Approximation with artificial neural networks, vol 24(48). MSc thesis, Faculty of Sciences, E\u00f6tv\u00f6s Lor\u00e1nd University, p 7"},{"key":"10213_CR28","unstructured":"Dai Z, Liu H, Le QV, Tan M (2021) Coatnet: marrying convolution and attention for all data sizes. arXiv preprint. arXiv:2106.04803"},{"key":"10213_CR29","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), vol 1. IEEE, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"10213_CR30","doi-asserted-by":"crossref","unstructured":"de Freitas Pereira T, Anjos A, De Martino JM, Marcel S (2013) Can face anti-spoofing countermeasures work in a real world scenario? In: Proceedings of the 2013 international conference on biometrics (ICB). IEEE, pp 1\u20138","DOI":"10.1109\/ICB.2013.6612981"},{"key":"10213_CR31","unstructured":"Denil M, Shakibi B, Dinh L, Ranzato M, Freitas ND (2013) Predicting parameters in deep learning. University of British Columbia, Vancouver"},{"key":"10213_CR32","unstructured":"Denton EL, Zaremba W, Bruna J, LeCun Y, Fergus R (2014) Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in neural information processing systems, pp 1269\u20131277"},{"key":"10213_CR33","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint. arXiv:1810.04805"},{"key":"10213_CR34","doi-asserted-by":"crossref","unstructured":"Dey N, Ren M, Dalca AV, Gerig G (2021) Generative adversarial registration for improved conditional deformable templates. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3929\u20133941","DOI":"10.1109\/ICCV48922.2021.00390"},{"key":"10213_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.07.002","volume":"96","author":"H Ding","year":"2019","unstructured":"Ding H, Chen K, Huo Q (2019a) Compressing CNN\u2013DBLSTM models for ocr with teacher\u2013student learning and Tucker decomposition. Pattern Recogn 96:106957","journal-title":"Pattern Recognition"},{"key":"10213_CR36","doi-asserted-by":"crossref","unstructured":"Ding R, Chin T-W, Liu Z, Marculescu D (2019b) Regularizing activation distribution for training binarized deep networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11408\u201311417","DOI":"10.1109\/CVPR.2019.01167"},{"key":"10213_CR37","doi-asserted-by":"crossref","unstructured":"Ding X, Hao T, Tan J, Liu J, Han J, Guo Y, Ding G (2021) ResRep: lossless CNN pruning via decoupling remembering and forgetting. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4510\u20134520","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"10213_CR38","doi-asserted-by":"crossref","unstructured":"Dong J-D, Cheng A-C, Juan D-C, Wei W, Sun M (2018) DPP-Net: deviceevice-aware progressive search for pareto-optimal neural architectures. In: Proceedings of the European conference on computer vision (ECCV), pp 517\u2013531","DOI":"10.1007\/978-3-030-01252-6_32"},{"key":"10213_CR39","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et\u00a0al (2020) An image is worth 16\u00a0\u00d7\u00a016 words: transformers for image recognition at scale. arXiv preprint. arXiv:2010.11929"},{"issue":"1","key":"10213_CR40","first-page":"1997","volume":"20","author":"T Elsken","year":"2019","unstructured":"Elsken T, Metzen JH, Hutter F (2019) Neural architecture search: a survey. J Mach Learn Res 20(1):1997\u20132017","journal-title":"Journal of Machine Learning Research"},{"issue":"7","key":"10213_CR41","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1109\/TIFS.2014.2322255","volume":"9","author":"N Erdogmus","year":"2014","unstructured":"Erdogmus N, Marcel S (2014) Spoofing face recognition with 3d masks. IEEE Trans Inf Forensics Security 9(7):1084\u20131097","journal-title":"IEEE transactions on information forensics and security"},{"key":"10213_CR42","doi-asserted-by":"crossref","unstructured":"Fang J, Sun Y, Zhang Q, Li Y, Liu W, Wang X (2020) Densely connected search space for more flexible neural architecture search. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10628\u201310637","DOI":"10.1109\/CVPR42600.2020.01064"},{"key":"10213_CR43","doi-asserted-by":"crossref","unstructured":"Fukushima K, Miyake S (1982) Neocognitron: a self-organizing neural network model for a mechanism of visual pattern recognition. In: Competition and cooperation in neural nets. Springer, Heidelberg, pp 267\u2013285","DOI":"10.1007\/978-3-642-46466-9_18"},{"key":"10213_CR44","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) YOLOX: exceeding YOLO Series in 2021. arXiv preprint. arXiv:2107.08430"},{"key":"10213_CR45","doi-asserted-by":"crossref","unstructured":"George A, Marcel S (2021) Cross modal focal loss for rgbd face anti-spoofing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7882\u20137891","DOI":"10.1109\/CVPR46437.2021.00779"},{"key":"10213_CR46","doi-asserted-by":"crossref","unstructured":"Fukushima K (1989) Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw 1:119\u2013130","DOI":"10.1016\/0893-6080(88)90014-7"},{"key":"10213_CR47","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"10213_CR48","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"10213_CR49","unstructured":"Gong Y, Liu L, Ming Y, Bourdev L (2014) Compressing deep convolutional networks using vector quantization. Comput Sci+++"},{"key":"10213_CR50","doi-asserted-by":"crossref","unstructured":"Graham B, El-Nouby A, Touvron H, Stock P, Joulin A, J\u00e9gou H, Douze M (2021) Levit: a vision transformer in convnet\u2019s clothing for faster inference. arXiv preprint. arXiv:2104.01136","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"10213_CR51","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Liu T, Wang X, Wang G, Cai J et al (2018) Recent advances in convolutional neural networks. Pattern Recogn 77:354\u2013377","journal-title":"Pattern Recognition"},{"key":"10213_CR52","doi-asserted-by":"crossref","unstructured":"Gulcehre C, Cho K, Pascanu R, Bengio Y (2014) Learned-norm pooling for deep feedforward and recurrent neural networks. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, pp. 530\u2013546","DOI":"10.1007\/978-3-662-44848-9_34"},{"key":"10213_CR55","unstructured":"Guo Y, Yao A, Chen Y (2016) Dynamic network surgery for efficient DNNs. arXiv preprint. arXiv:1608.04493"},{"key":"10213_CR53","doi-asserted-by":"crossref","unstructured":"Guo Z, Zhang X, Mu H, Heng W, Liu Z, Wei Y, Sun J (2020) Single path one-shot neural architecture search with uniform sampling. In: European conference on computer vision. Springer, Munich, pp 544\u2013560","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"10213_CR54","doi-asserted-by":"crossref","unstructured":"Guo J, Han K, Wang Y, Wu H, Chen X, Xu C, Xu C (2021) Distilling object detectors via decoupled features. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2154\u20132164","DOI":"10.1109\/CVPR46437.2021.00219"},{"issue":"4","key":"10213_CR56","first-page":"3","volume":"56","author":"S Han","year":"2015","unstructured":"Han S, Mao H, Dally WJ (2015a) Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. Fiber 56(4):3\u20137","journal-title":"Fiber"},{"key":"10213_CR58","unstructured":"Han S, Pool J, Tran J, Dally WJ (2015b) Learning both weights and connections for efficient neural networks. MIT, Cambridge"},{"key":"10213_CR57","doi-asserted-by":"crossref","unstructured":"Han D, Kim J, Kim J (2017) Deep pyramidal residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5927\u20135935","DOI":"10.1109\/CVPR.2017.668"},{"key":"10213_CR59","first-page":"177","volume":"1","author":"S Hanson","year":"1988","unstructured":"Hanson S, Pratt L (1988) Comparing biases for minimal network construction with back-propagation. Adv Neural Inf Process Syst 1:177\u2013185","journal-title":"Advances in neural information processing systems"},{"key":"10213_CR60","unstructured":"Hassibi B, Stork DG, Wolff G, Watanabe T (1994) Optimal brain surgeon: extensions and performance comparison. In: Cowan JD, Tesauro G, Alspector J (eds) Advances in neural information processing systems, vol 6. Morgan Kaufmann, San Mateo, pp 263\u2013270"},{"issue":"2","key":"10213_CR61","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/BF01272517","volume":"1","author":"J H\u00e5stad","year":"1991","unstructured":"H\u00e5stad J, Goldmann M (1991) On the power of small-depth threshold circuits. Comput Complex 1(2):113\u2013129","journal-title":"Computational Complexity"},{"key":"10213_CR63","doi-asserted-by":"crossref","unstructured":"He K, Sun J (2015) Convolutional neural networks at constrained time cost. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5353\u20135360","DOI":"10.1109\/CVPR.2015.7299173"},{"issue":"9","key":"10213_CR62","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015a) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10213_CR64","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015b) Delving deep into rectifiers: surpassing human-level performance on ImageNet  classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"10213_CR65","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10213_CR66","doi-asserted-by":"crossref","unstructured":"He Y, Zhang X, Sun J (2017) Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 1389\u20131397","DOI":"10.1109\/ICCV.2017.155"},{"issue":"5786","key":"10213_CR67","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"issue":"7","key":"10213_CR68","first-page":"38","volume":"14","author":"G Hinton","year":"2015","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. Comput Sci 14(7):38\u201339","journal-title":"Computer Science"},{"key":"10213_CR69","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint. arXiv:1704.04861"},{"key":"10213_CR70","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G, Chen L-C, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V et\u00a0al (2019) Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"10213_CR75","doi-asserted-by":"crossref","unstructured":"Hua W, Zhou Y, De\u00a0Sa C, Zhang Z, Suh GE (2019) Boosting the performance of cnn accelerators with dynamic fine-grained channel gating. In: Proceedings of the 52nd Annual IEEE\/ACM international symposium on microarchitecture, pp 139\u2013150","DOI":"10.1145\/3352460.3358283"},{"key":"10213_CR73","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"10213_CR74","doi-asserted-by":"crossref","unstructured":"Huang G, Liu S, Van\u00a0der Maaten L, Weinberger KQ (2018) Condensenet: an efficient densenet using learned group convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2752\u20132761","DOI":"10.1109\/CVPR.2018.00291"},{"key":"10213_CR71","doi-asserted-by":"crossref","unstructured":"Huang X, Xu J, Tai Y-W, Tang C-K (2020) Fast video object segmentation with temporal aggregation network and dynamic template matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8879\u20138889","DOI":"10.1109\/CVPR42600.2020.00890"},{"key":"10213_CR72","doi-asserted-by":"crossref","unstructured":"Huang H, Zhang J, Shan H (2021) When age-invariant face recognition meets face age synthesis: a multi-task learning framework. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7282\u20137291","DOI":"10.1109\/CVPR46437.2021.00720"},{"issue":"1","key":"10213_CR77","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1113\/jphysiol.1962.sp006837","volume":"160","author":"DH Hubel","year":"1962","unstructured":"Hubel DH, Wiesel TN (1962) Receptive fields, binocular interaction and functional architecture in the cat\u2019s visual cortex. J Physiol 160(1):106\u2013154","journal-title":"The Journal of physiology"},{"key":"10213_CR76","doi-asserted-by":"crossref","unstructured":"Hubel DH, Wiesel TN (2009) Republication of The Journal of Physiology (1959) 148, 574-591: Receptive fields of single neurones in the cat's striate cortex. 1959. J Physiol 587(Pt 12):2721\u20132732","DOI":"10.1113\/jphysiol.1959.sp006308"},{"key":"10213_CR78","unstructured":"Hu H, Peng R, Tai YW, Tang CK (2016) Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint. arXiv:1607.03250"},{"key":"10213_CR79","doi-asserted-by":"crossref","unstructured":"Hu Q, Wang P, Cheng J (2018) From hashing to CNNs: training binary weight networks via hashing. In: 32nd AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11660"},{"key":"10213_CR80","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning (PMLR), pp 448\u2013456"},{"issue":"4","key":"10213_CR81","first-page":"XIII","volume":"4","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Speeding up convolutional neural networks with low rank expansions. Comput Sci 4(4):XIII","journal-title":"Computer ence"},{"issue":"1","key":"10213_CR82","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2010","unstructured":"Jegou H, Douze M, Schmid C (2010) Product quantization for nearest neighbor search. IEEE Trans Pattern Anal Mach Intell 33(1):117\u2013128","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10213_CR83","doi-asserted-by":"crossref","unstructured":"Ji G-P, Fu K, Wu Z, Fan D-P, Shen J, Shao L (2021) Full-duplex strategy for video object segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision, pp 4922\u20134933","DOI":"10.1109\/ICCV48922.2021.00488"},{"key":"10213_CR85","doi-asserted-by":"crossref","unstructured":"Ji M, Shin S, Hwang S, Park G, Moon I-C (2021) Refine myself by teaching myself: Feature refinement via self-knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10664\u201310673","DOI":"10.1109\/CVPR46437.2021.01052"},{"key":"10213_CR84","unstructured":"Jia Y et\u00a0al (2013) An open source convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, Orlando, FL, pp 675\u2013678"},{"key":"10213_CR87","doi-asserted-by":"crossref","unstructured":"Jo G, Lee G, Shin D (2020) Exploring group sparsity using dynamic sparse training. In: 2020 IEEE international conference on consumer electronics-Asia (ICCE-Asia). IEEE, pp 1\u20132","DOI":"10.1109\/ICCE-Asia49877.2020.9277137"},{"key":"10213_CR86","unstructured":"Jocher G (2020) Yolo v5. https:\/\/github.com\/ultralytics\/yolov5 Accessed July 2020"},{"issue":"8","key":"10213_CR88","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan A, Sohail A, Zahoora U, Qureshi AS (2020) A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 53(8):5455\u20135516","journal-title":"Artificial Intelligence Review"},{"issue":"2","key":"10213_CR90","first-page":"576","volume":"71","author":"YD Kim","year":"2015","unstructured":"Kim YD, Park E, Yoo S, Choi T, Yang L, Shin D (2015) Compression of deep convolutional neural networks for fast and low power mobile applications. Comput Sci 71(2):576\u2013584","journal-title":"Computer Science"},{"key":"10213_CR89","doi-asserted-by":"crossref","unstructured":"Kim S-W, Kook H-K, Sun J-Y, Kang M-C, Ko S-J (2018) Parallel feature pyramid network for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 234\u2013250","DOI":"10.1007\/978-3-030-01228-1_15"},{"key":"10213_CR91","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Tan C, Liu H, Huang W (2018) Deep feature pyramid reconfiguration for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 169\u2013185","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"10213_CR92","unstructured":"Kozyrskiy N, Phan A-H (2020) Cnn acceleration by low-rank approximation with quantized factors. arXiv preprint. arXiv:2006.08878"},{"key":"10213_CR93","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Advances in neural information processing systems"},{"key":"10213_CR94","doi-asserted-by":"crossref","unstructured":"Lai Z, Lu E, Xie W (2020) Mast: a memory-augmented self-supervised tracker. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6479\u20136488","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"10213_CR96","doi-asserted-by":"crossref","unstructured":"Lebedev V, Lempitsky V (2016) Fast convnets using group-wise brain damage. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2554\u20132564","DOI":"10.1109\/CVPR.2016.280"},{"key":"10213_CR95","unstructured":"Lebedev V, Ganin Y, Rakhuba M, Oseledets I, Lempitsky V (2014) Speeding-up convolutional neural networks using fine-tuned cp-decomposition. In: International conference on learning representations (ICLR Poster)"},{"key":"10213_CR98","unstructured":"LeCun Y, Denker JS, Solla SA (1990) Optimal brain damage. In: Touretzky DS (ed) Advances in neural information processing systems. Morgan Kaufmann, San Francisco, pp 598\u2013605"},{"issue":"11","key":"10213_CR97","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"10213_CR99","doi-asserted-by":"crossref","unstructured":"LeCun Y, Kavukcuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE international symposium on circuits and systems. IEEE, pp 253\u2013256","DOI":"10.1109\/ISCAS.2010.5537907"},{"issue":"7","key":"10213_CR100","doi-asserted-by":"publisher","first-page":"1625","DOI":"10.1109\/JSSC.2013.2253226","volume":"48","author":"KH Lee","year":"2013","unstructured":"Lee KH, Verma N (2013) A low-power processor with configurable embedded machine-learning accelerators for high-order and adaptive analysis of medical-sensor signals. IEEE J Solid-State Circuits 48(7):1625\u20131637","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"10213_CR103","doi-asserted-by":"crossref","unstructured":"Lee H, Wu Y-H, Lin Y-S, Chien S-Y (2019) Convolutional neural network accelerator with vector quantization. In: 2019 IEEE international symposium on circuits and systems (ISCAS). IEEE, pp 1\u20135","DOI":"10.1109\/ISCAS.2019.8702105"},{"key":"10213_CR101","doi-asserted-by":"crossref","unstructured":"Lee K, Kim H, Lee H, Shin D (2020) Flexible group-level pruning of deep neural networks for on-device machine learning. In: 2020 Design, automation & test in Europe cnference & exhibition (DATE). IEEE, pp 79\u201384","DOI":"10.23919\/DATE48585.2020.9116287"},{"key":"10213_CR102","doi-asserted-by":"crossref","unstructured":"Lee D, Wang D, Yang Y, Deng L, Zhao G, Li G (2021) QTTNet: quantized tensor train neural networks for 3D object and video recognition. Neural Netw 141:420\u2013432","DOI":"10.1016\/j.neunet.2021.05.034"},{"key":"10213_CR104","doi-asserted-by":"crossref","unstructured":"Leng C, Dou Z, Li H, Zhu S, Jin R (2018) Extremely low bit neural network: Squeeze the last bit out with ADMM. In: Thirty-Second AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"10213_CR126","unstructured":"Li F, Zhang B, Liu B (2016) Ternary weight networks. arXiv preprint. arXiv:1605.04711"},{"key":"10213_CR109","unstructured":"Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2016) Pruning filters for efficient convnets. arXiv preprint. arXiv:1608.08710"},{"issue":"12","key":"10213_CR106","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1587\/transinf.2019EDL8118","volume":"102","author":"L Li","year":"2019","unstructured":"Li L, Zhu J, Sun M-T (2019) A spectral clustering based filter-level pruning method for convolutional neural networks. IEICE Trans Inf Syst 102(12):2624\u20132627","journal-title":"IEICE TRANSACTIONS on Information and Systems"},{"key":"10213_CR105","doi-asserted-by":"crossref","unstructured":"Li C, Wang G, Wang B, Liang X, Li Z, Chang X (2021a) Dynamic slimmable network. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 8607\u20138617","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"10213_CR107","doi-asserted-by":"crossref","unstructured":"Li Y, Ding W, Liu C, Zhang B, Guo G (2021b) TRQ: Ternary neural networks with residual quantization. In:  Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v35i10.17036"},{"key":"10213_CR108","doi-asserted-by":"crossref","unstructured":"Li Y, Gu S, Mayer C, Gool LV, Timofte R (2020) Group sparsity: The hinge between filter pruning and decomposition for network compression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8018\u20138027","DOI":"10.1109\/CVPR42600.2020.00804"},{"key":"10213_CR111","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv preprint. arXiv:1312.4400"},{"key":"10213_CR113","unstructured":"Lin D, Talathi S, Annapureddy S (2016) Fixed point quantization of deep convolutional networks. In: International conference on machine learning (PMLR), pp 2849\u20132858"},{"key":"10213_CR114","unstructured":"Lin X, Zhao C, Pan W (2017a) Towards accurate binary convolutional neural network. In: Advances in neural information processing systems"},{"key":"10213_CR110","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017b) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"10213_CR112","doi-asserted-by":"crossref","unstructured":"Lin R, Ko C-Y, He Z, Chen C, Cheng Y, Yu H, Chesi G, Wong N (2020) Hotcake: higher order tucker articulated kernels for deeper CNN compression. In: 2020 IEEE 15th international conference on solid-state & integrated circuit technology (ICSICT). IEEE, pp 1\u20134","DOI":"10.1109\/ICSICT49897.2020.9278257"},{"key":"10213_CR123","unstructured":"Liu B, Wang M, Foroosh H, Tappen M, Pensky M (2015) Sparse convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 806\u2013814"},{"key":"10213_CR116","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10213_CR120","doi-asserted-by":"crossref","unstructured":"Liu Z, Li J, Shen Z, Huang G, Yan S, Zhang C (2017) Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE international conference on computer vision, pp 2736\u20132744","DOI":"10.1109\/ICCV.2017.298"},{"key":"10213_CR115","doi-asserted-by":"crossref","unstructured":"Liu C, Zoph B, Neumann M, Shlens J, Hua W, Li L-J, Fei-Fei L, Yuille A, Huang J, Murphy K (2018a) Progressive neural architecture search. In: Proceedings of the European conference on computer vision (ECCV), pp 19\u201334","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"10213_CR121","unstructured":"Liu X, Pool J, Han S, Dally WJ (2018b) Efficient sparse-Winograd convolutional neural networks. arXiv preprint. arXiv:1802.06367"},{"key":"10213_CR117","doi-asserted-by":"crossref","unstructured":"Liu C, Chen L-C, Schroff F, Adam H, Hua W, Yuille AL, Fei-Fei L (2019) Auto-deeplab: hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 82\u201392","DOI":"10.1109\/CVPR.2019.00017"},{"key":"10213_CR122","doi-asserted-by":"crossref","unstructured":"Liu Z, Shen Z, Savvides M, Cheng K-T (2020a) Reactnet: towards precise binary neural network with generalized activation functions. In: European conference on computer vision. Springer, Berlin, pp 143\u2013159","DOI":"10.1007\/978-3-030-58568-6_9"},{"key":"10213_CR124","unstructured":"Liu J, Xu Z, Shi R, Cheung RC, So HK (2020b) Dynamic sparse training: Find efficient sparse network from scratch with trainable masked layers. arXiv preprint. arXiv:2005.06870"},{"key":"10213_CR118","unstructured":"Liu D, Chen X, Fu J, Liu X (2021a) Pruning ternary quantization. arXiv preprint. arXiv:2107.10998"},{"key":"10213_CR119","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021b) Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint. arXiv:2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10213_CR125","unstructured":"Liu L, Zhang S, Kuang Z, Zhou A, Xue J-H, Wang X, Chen Y, Yang W, Liao Q, Zhang W (2021c) Group fisher pruning for practical network compression. In: International conference on machine learning (PMLR), pp 7021\u20137032"},{"issue":"2","key":"10213_CR127","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"International journal of computer vision"},{"key":"10213_CR130","doi-asserted-by":"crossref","unstructured":"Lu Z, Whalen I, Boddeti V, Dhebar Y, Deb K, Goodman E, Banzhaf W (2019) NSGA-Net: neural architecture search using multi-objective genetic algorithm. In: Proceedings of the genetic and evolutionary computation conference, pp 419\u2013427","DOI":"10.1145\/3321707.3321729"},{"key":"10213_CR129","doi-asserted-by":"crossref","unstructured":"Luo P, Zhu Z, Liu Z, Wang X, Tang X (2016) Face model compression by distilling knowledge from neurons. In: Proceedings of the 30th AAAI conference on artificial intelligence. AAAI, Phoenix","DOI":"10.1609\/aaai.v30i1.10449"},{"key":"10213_CR128","doi-asserted-by":"crossref","unstructured":"Luo J-H, Wu J, Lin W (2017) Thinet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE international conference on computer vision, pp 5058\u20135066","DOI":"10.1109\/ICCV.2017.541"},{"key":"10213_CR135","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng H-T, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"10213_CR131","doi-asserted-by":"crossref","unstructured":"Ma X, Guo F-M, Niu W, Lin X, Tang J, Ma K, Ren B, Wang Y (2020) PCONV: the missing but desirable sparsity in DNN weight pruning for real-time execution on mobile devices. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 5117\u20135124","DOI":"10.1609\/aaai.v34i04.5954"},{"key":"10213_CR132","unstructured":"Maas AL, Hannun AY, Ng AY, et\u00a0al (2013) Rectifier nonlinearities improve neural network acoustic models. Proc ICML 30:3. Citeseer"},{"key":"10213_CR134","doi-asserted-by":"crossref","unstructured":"Mao H, Han S, Pool J, Li W, Liu X, Wang Y, Dally WJ (2017) Exploring the regularity of sparse structure in convolutional neural networks. arXiv preprint. arXiv:1705.08922","DOI":"10.1109\/CVPRW.2017.241"},{"key":"10213_CR133","doi-asserted-by":"crossref","unstructured":"Mao Y, Wang N, Zhou W, Li H (2021) Joint inductive and transductive learning for video object segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9670\u20139679","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"10213_CR136","unstructured":"Maziarz K, Tan M, Khorlin A, Chang K-YS, Gesmundo A (2019) Evo-nas: Evolutionary-neural hybrid agent for architecture search"},{"key":"10213_CR137","unstructured":"Mehta S, Rastegari M (2021) MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint. arXiv:2110.02178"},{"key":"10213_CR138","unstructured":"Michel G, Alaoui MA, Lebois A, Feriani A, Felhi M (2019) Dvolver: Efficient pareto-optimal neural network architecture search. arXiv preprint. arXiv:1902.01654"},{"key":"10213_CR139","unstructured":"Mikolov T, Karafi\u00e1t M, Burget L, \u010cernocky J, Khudanpur S (2010) Eleventh annual conference of the international speech communication association"},{"issue":"9","key":"10213_CR140","first-page":"468","volume":"7","author":"M Montremerlo","year":"2008","unstructured":"Montremerlo M, Beeker J, Bhat S, Dahlkamp H (2008) The stanford entry in the urban challenge. J Field Robot 7(9):468\u2013492","journal-title":"Journal of Field Robotics"},{"key":"10213_CR141","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: International conference on international conference on machine learning (ICML)"},{"issue":"8","key":"10213_CR142","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1109\/TVLSI.2019.2905242","volume":"27","author":"DT Nguyen","year":"2019","unstructured":"Nguyen DT, Nguyen TN, Kim H, Lee H-J (2019) A high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection. IEEE Trans Very Large Scale Integr (VLSI) Syst 27(8):1861\u20131873","journal-title":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems"},{"key":"10213_CR143","doi-asserted-by":"crossref","unstructured":"Niu W, Ma X, Lin S, Wang S, Qian X, Lin X, Wang Y, Ren B (2020) PatDNN: achieving real-time DNN execution on mobile devices with pattern-based weight pruning. In: Proceedings of the 25th international conference on architectural support for programming languages and operating systems, pp 907\u2013922","DOI":"10.1145\/3373376.3378534"},{"key":"10213_CR144","unstructured":"Novikov A, Podoprikhin D, Osokin A, Vetrov D (2015) Tensorizing neural networks. arXiv preprint. arXiv:1509.06569"},{"issue":"5","key":"10213_CR145","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets IV (2011) Tensor-train decomposition. SIAM J Sci Comput 33(5):2295\u20132317","journal-title":"SIAM Journal on Scientific Computing"},{"key":"10213_CR146","doi-asserted-by":"crossref","unstructured":"Peng Z, Huang W, Gu S, Xie L, Wang Y, Jiao J, Ye Q (2021) Conformer: local features coupling global representations for visual recognition. arXiv preprint. arXiv:2105.03889","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"10213_CR147","unstructured":"Perez-Rua J-M, Baccouche M, Pateux S (2018) Efficient progressive neural architecture search. arXiv preprint. arXiv:1808.00391"},{"issue":"5","key":"10213_CR148","doi-asserted-by":"publisher","first-page":"3299","DOI":"10.1007\/s10462-019-09765-w","volume":"53","author":"P Punyani","year":"2020","unstructured":"Punyani P, Gupta R, Kumar A (2020) Neural networks for facial age estimation: a survey on recent advances. Artif Intell Rev 53(5):3299\u20133347","journal-title":"Artificial Intelligence Review"},{"key":"10213_CR149","doi-asserted-by":"crossref","unstructured":"Qin Z, Li Z, Zhang Z, Bao Y, Yu G, Peng Y, Sun J (2019) Thundernet: towards real-time generic object detection on mobile devices. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6718\u20136727","DOI":"10.1109\/ICCV.2019.00682"},{"key":"10213_CR151","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training"},{"issue":"8","key":"10213_CR150","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I et al (2019) Language models are unsupervised multitask learners. OpenAI Blog 1(8):9","journal-title":"OpenAI blog"},{"key":"10213_CR152","doi-asserted-by":"crossref","unstructured":"Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) XNOR-Net: Imagenet classification using binary convolutional neural networks. In: European conference on computer vision. Springer, Cham, pp 525\u2013542","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"10213_CR153","doi-asserted-by":"crossref","unstructured":"Razani R, Morin G, Sari E, Nia VP (2021) Adaptive binary-ternary quantization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4613\u20134618","DOI":"10.1109\/CVPRW53098.2021.00519"},{"key":"10213_CR154","doi-asserted-by":"crossref","unstructured":"Real E, Aggarwal A, Huang Y, Le QV (2019) Regularized evolution for image classifier architecture search. In: Proceedings of the aaai conference on artificial intelligence, vol 33, pp 4780\u20134789","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"10213_CR155","doi-asserted-by":"crossref","unstructured":"Redfern AJ, Zhu L, Newquist MK (2021) BCNN: a binary CNN with all matrix OPS quantized to 1 bit precision. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4604\u20134612","DOI":"10.1109\/CVPRW53098.2021.00518"},{"key":"10213_CR157","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"10213_CR158","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint. arXiv:1804.02767"},{"key":"10213_CR156","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"10213_CR159","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91\u201399","journal-title":"Advances in neural information processing systems"},{"key":"10213_CR160","unstructured":"Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2014) Fitnets: Hints for thin deep nets. rXiv preprint. arXiv:1412.6550"},{"key":"10213_CR161","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101587","volume":"59","author":"AG Roy","year":"2020","unstructured":"Roy AG, Siddiqui S, P\u00f6lsterl S, Navab N, Wachinger C (2020) squeeze & exciteguided few-shot segmentation of volumetric images. Med Image Anal 59:101587","journal-title":"Medical image analysis"},{"key":"10213_CR162","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10213_CR163","doi-asserted-by":"crossref","unstructured":"Seong H, Hyun J, Kim E (2020) Kernelized memory network for video object segmentation. In: European conference on computer vision. Springer, Cham, pp 629\u2013645","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"10213_CR164","doi-asserted-by":"crossref","unstructured":"Sharma M, Markopoulos PP, Saber E, Asif MS, Prater-Bennette A (2021) Convolutional auto-encoder with tensor-train factorization. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 198\u2013206","DOI":"10.1109\/ICCVW54120.2021.00027"},{"key":"10213_CR165","unstructured":"Simard PY, Steinkraus D, Platt JC et\u00a0al (2003) Best practices for convolutional neural networks applied to visual document analysis. In: ICDAR, vol 3"},{"key":"10213_CR166","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arxiv preprint. arXiv:1409.1556"},{"key":"10213_CR168","doi-asserted-by":"publisher","unstructured":"Srinivas S, Babu RV (2015) Data-free parameter pruning for deep neural networks. Comput Sci. https:\/\/doi.org\/10.5244\/C.29.31","DOI":"10.5244\/C.29.31"},{"key":"10213_CR167","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3389\/frobt.2015.00036","volume":"2","author":"S Srinivas","year":"2016","unstructured":"Srinivas S, Sarvadevabhatla RK, Mopuri KR, Prabhu N, Kruthiventi SS, Babu RV (2016) A taxonomy of deep convolutional neural nets for computer vision. Front Robotics AI 2:36","journal-title":"Frontiers in Robotics and AI"},{"key":"10213_CR169","doi-asserted-by":"crossref","unstructured":"Srinivas A, Lin T-Y, Parmar N, Shlens J, Abbeel P, Vaswani A (2021) Bottleneck transformers for visual recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16519\u201316529","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"10213_CR170","unstructured":"Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Advances in neural information processing systems"},{"key":"10213_CR172","unstructured":"Sun W, Zhou A, Stuijk S, Wijnhoven R, Nelson AO, Corporaal H et\u00a0al (2021) DominoSearch: find layer-wise fine-grained N:M sparse schemes from dense neural networks. In: Advances in neural information processing systems 34 (NeurIPS 2021)"},{"key":"10213_CR171","doi-asserted-by":"crossref","unstructured":"Sundermeyer M, Schl\u00fcter R, Ney H (2012) Lstm neural networks for language modeling. In: 13th annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2012-65"},{"key":"10213_CR174","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10213_CR173","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: 31st AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"10213_CR175","doi-asserted-by":"crossref","unstructured":"Takahashi N, Mitsufuji Y (2021) Densely connected multi-dilated convolutional networks for dense prediction tasks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 993\u20131002","DOI":"10.1109\/CVPR46437.2021.00105"},{"key":"10213_CR176","doi-asserted-by":"crossref","unstructured":"Tan M, Chen B, Pang R, Vasudevan V, Sandler M, Howard A, Le QV (2019) Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2820\u20132828","DOI":"10.1109\/CVPR.2019.00293"},{"key":"10213_CR178","doi-asserted-by":"crossref","unstructured":"Tang W, Hua G, Wang L (2017) How to train a compact binary neural network with high accuracy? In: 31st  AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.10862"},{"key":"10213_CR177","doi-asserted-by":"crossref","unstructured":"Tang H, Liu X, Sun S, Yan X, Xie X (2021a) Recurrent mask refinement for few-shot medical image segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3918\u20133928","DOI":"10.1109\/ICCV48922.2021.00389"},{"key":"10213_CR179","doi-asserted-by":"crossref","unstructured":"Tang Y, Wang Y, Xu Y, Deng Y, Xu C, Tao D, Xu C (2021a) Manifold regularized dynamic network pruning. In: Proceedings of the IEEE\/CVF international conference on computer vision and pattern recognition, pp 5018\u20135028","DOI":"10.1109\/CVPR46437.2021.00498"},{"key":"10213_CR180","unstructured":"Theis L, Korshunova I, Tejani A, Husz\u00e1r F (2018) Faster gaze prediction with dense networks and fisher pruning. arXiv preprint. arXiv:1801.05787"},{"key":"10213_CR181","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H (2021) Training data-efficient image transformers and distillation through attention. In: International conference on machine learning (PMLR), pp 10347\u201310357"},{"issue":"2","key":"10213_CR182","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vis 104(2):154\u2013171","journal-title":"International journal of computer vision"},{"key":"10213_CR183","unstructured":"Vanhoucke V, Senior A, Mao MZ (2011) Improving the speed of neural networks on CPUS. In: Deep learning and unsupervised feature learning workshop"},{"key":"10213_CR184","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"10213_CR191","doi-asserted-by":"crossref","unstructured":"Wang P, Cheng J (2016) Accelerating convolutional neural networks for mobile applications. In: Proceedings of the 24th ACM international conference on Multimedia, pp 541\u2013545","DOI":"10.1145\/2964284.2967280"},{"key":"10213_CR192","doi-asserted-by":"crossref","unstructured":"Wang P, Cheng J (2017) Fixed-point factorized networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4012\u20134020","DOI":"10.1109\/CVPR.2017.422"},{"key":"10213_CR194","doi-asserted-by":"crossref","unstructured":"Wang P, Hu Q, Zhang Y, Zhang C, Liu Y, Cheng J (2018) Two-step quantization for low-bit neural networks. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 4376\u20134384","DOI":"10.1109\/CVPR.2018.00460"},{"key":"10213_CR189","doi-asserted-by":"publisher","first-page":"175703","DOI":"10.1109\/ACCESS.2019.2957203","volume":"7","author":"Z Wang","year":"2019","unstructured":"Wang Z, Lin S, Xie J, Lin Y (2019a) Pruning blocks for cnn compression and acceleration via online ensemble distillation. IEEE Access 7:175703\u2013175716","journal-title":"IEEE Access"},{"key":"10213_CR193","doi-asserted-by":"crossref","unstructured":"Wang W, Fu C, Guo J, Cai D, He X (2019b) COP: customized deep model compression via regularized correlation-based filter-level pruning. Neurocomputing 464:533\u2013545","DOI":"10.1016\/j.neucom.2021.08.098"},{"key":"10213_CR196","doi-asserted-by":"crossref","unstructured":"Wang Z, Lu J, Tao C, Zhou J, Tian Q (2019c) Learning channel-wise interactions for binary convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 568\u2013577","DOI":"10.1109\/CVPR.2019.00066"},{"key":"10213_CR185","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Liao H-YM, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H (2020a) Cspnet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 390\u2013391","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"10213_CR188","unstructured":"Wang N, Zhou W, Li H (2020b) Contrastive transformation for self-supervised correspondence learning. arXiv preprint. arXiv:2012.05057"},{"key":"10213_CR186","doi-asserted-by":"crossref","unstructured":"Wang D, Li M, Gong C, Chandra V (2021a) Attentivenas: improving neural architecture search via attentive sampling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6418\u20136427","DOI":"10.1109\/CVPR46437.2021.00635"},{"key":"10213_CR187","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu Z, Wang X, Shen C, Cheng B, Shen H, Xia H (2021b) End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8741\u20138750","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"10213_CR190","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.neunet.2021.08.028","volume":"144","author":"D Wang","year":"2021","unstructured":"Wang D, Zhao G, Chen H, Liu Z, Deng L, Li G (2021c) Nonlinear tensor train format for deep neural network compression. Neural Netw 144:320\u2013333","journal-title":"Neural Networks"},{"key":"10213_CR195","doi-asserted-by":"crossref","unstructured":"Wang C, Liu B, Liu L, Zhu Y, Hou J, Liu P, Li X (2021d) A review of deep learning used in the hyperspectral image analysis for agriculture. Artif Intell Rev 54:5205\u20135253","DOI":"10.1007\/s10462-021-10018-y"},{"key":"10213_CR197","doi-asserted-by":"crossref","unstructured":"Wang Z, Xiao H, Lu J, Zhou J (2021e) Generalizable mixed-precision quantization via attribution rank preservation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 5291\u20135300","DOI":"10.1109\/ICCV48922.2021.00524"},{"key":"10213_CR198","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Fan D-P, Song K, Liang D, Lu T, Luo P, Shao L (2021f) Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv preprint. arXiv:2102.12122","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10213_CR199","first-page":"2074","volume":"29","author":"W Wen","year":"2016","unstructured":"Wen W, Wu C, Wang Y, Chen Y, Li H (2016) Learning structured sparsity in deep neural networks. Adv Neural Inf Process Syst 29:2074\u20132082","journal-title":"Advances in neural information processing systems"},{"key":"10213_CR200","unstructured":"Wen W, Xu C, Yan F, Wu C, Wang Y, Chen Y, Li H (2017) Terngrad: Ternary gradients to reduce communication in distributed deep learning. arXiv preprint. arXiv:1705.07878"},{"key":"10213_CR201","doi-asserted-by":"crossref","unstructured":"Wu J, Leng C, Wang Y, Hu Q, Cheng J (2016) Quantized convolutional neural networks for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4820\u20134828","DOI":"10.1109\/CVPR.2016.521"},{"key":"10213_CR202","doi-asserted-by":"crossref","unstructured":"Wu Y, Wu Y, Gong R, Lv Y, Chen K, Liang D, Hu X, Liu X, Yan J (2020a) Rotation consistent margin loss for efficient low-bit face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6866\u20136876","DOI":"10.1109\/CVPR42600.2020.00690"},{"key":"10213_CR203","unstructured":"Wu B, Xu C, Dai X, Wan A, Zhang P, Yan Z, Tomizuka M, Gonzalez J, Keutzer K, Vajda P (2020b) Visual transformers: token-based image representation and processing for computer vision. arXiv preprint. arXiv:2006.03677"},{"key":"10213_CR205","doi-asserted-by":"crossref","unstructured":"Xie L, Yuille A (2017) Genetic CNN. In: Proceedings of the IEEE international conference on computer vision, pp 1379\u20131388","DOI":"10.1109\/ICCV.2017.154"},{"key":"10213_CR204","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"10213_CR206","doi-asserted-by":"crossref","unstructured":"Xu H (2020) Pnfm: a filter level pruning method for cnn compression. In: Proceedings of the 3rd international conference on information technologies and electrical engineering, pp 49\u201354","DOI":"10.1145\/3452940.3452950"},{"key":"10213_CR208","unstructured":"Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprint. arXiv:1505.00853"},{"key":"10213_CR207","unstructured":"Xu Y, Xie L, Zhang X, Chen X, Qi G-J, Tian Q, Xiong H (2019) PC-DARTS: partial channel connections for memory-efficient architecture search. arXiv preprint. arXiv:1907.05737"},{"key":"10213_CR209","doi-asserted-by":"crossref","unstructured":"Xu Y, Wang Y, Han K, Tang Y, Jui S, Xu C, Xu C (2021) Renas: relativistic evaluation of neural architecture search. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4411\u20134420","DOI":"10.1109\/CVPR46437.2021.00439"},{"key":"10213_CR210","doi-asserted-by":"crossref","unstructured":"Yamamoto K (2021) Learnable companding quantization for accurate low-bit neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5029\u20135038","DOI":"10.1109\/CVPR46437.2021.00499"},{"key":"10213_CR212","doi-asserted-by":"crossref","unstructured":"Yang Z, Wang Y, Chen X, Shi B, Xu C, Xu C, Tian Q, Xu C (2020a) CARS: continuous evolution for efficient neural architecture search. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1829\u20131838","DOI":"10.1109\/CVPR42600.2020.00190"},{"key":"10213_CR213","unstructured":"Yang Z, Wang Y, Han K, Xu C, Xu C, Tao D, Xu C (2020b) Searching for low-bit weights in quantized neural networks. arXiv preprint. arXiv:2009.08695"},{"key":"10213_CR211","doi-asserted-by":"crossref","unstructured":"Yang Z,  Wang Y, Chen X, Guo J, Zhang W, Xu C, Xu C, Tao D, Xu C (2021) Hournas: extremely fast neural architecture search through an hourglass lens. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10896\u201310906","DOI":"10.1109\/CVPR46437.2021.01075"},{"key":"10213_CR214","doi-asserted-by":"crossref","unstructured":"Yao L, Pi R, Xu H, Zhang W, Li Z, Zhang T (2021) G-DetKD: towards general distillation framework for object detectors via contrastive and semantic-guided feature imitation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3591\u20133600","DOI":"10.1109\/ICCV48922.2021.00357"},{"key":"10213_CR216","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neunet.2020.05.034","volume":"130","author":"J Ye","year":"2020","unstructured":"Ye J, Li G, Chen D, Yang H, Zhe S, Xu Z (2020) Block-term tensor neural networks. Neural Netw 130:11\u201321","journal-title":"Neural Networks"},{"key":"10213_CR215","doi-asserted-by":"crossref","unstructured":"Ye M, Kanski M, Yang D, Chang Q, Yan Z, Huang Q, Axel L, Metaxas D (2021) DeepTag: an unsupervised deep learning method for motion tracking on cardiac tagging magnetic resonance images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7261\u20137271","DOI":"10.1109\/CVPR46437.2021.00718"},{"key":"10213_CR218","doi-asserted-by":"crossref","unstructured":"Yuan L, Wang T, Zhang X, Tay FE, Jie Z, Liu W, Feng J (2020) Central similarity quantization for efficient image and video retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3083\u20133092","DOI":"10.1109\/CVPR42600.2020.00315"},{"key":"10213_CR217","doi-asserted-by":"crossref","unstructured":"Yuan L, Chen Y, Wang T, Yu W, Shi Y, Jiang Z, Tay FE, Feng J, Yan S (2021) Tokens-to-token vit: training vision transformers from scratch on imagenet. arXiv preprint. arXiv:2101.11986","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"10213_CR219","unstructured":"Zagoruyko S, Komodakis N (2016a) Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint. arXiv:1612.03928"},{"key":"10213_CR220","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016b) Wide residual networks, British Machine Vision Conference","DOI":"10.5244\/C.30.87"},{"key":"10213_CR221","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, Cham, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"10","key":"10213_CR222","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1109\/TPAMI.2015.2502579","volume":"38","author":"X Zhang","year":"2015","unstructured":"Zhang X, Zou J, He K, Sun J (2015) Accelerating very deep convolutional networks for classification and detection. IEEE Trans Pattern Anal Mach Intell 38(10):1943\u20131955","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10213_CR223","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.neucom.2018.09.038","volume":"323","author":"Q Zhang","year":"2019","unstructured":"Zhang Q, Zhang M, Chen T, Sun Z, Ma Y, Yu B (2019) Recent advances in convolutional neural network acceleration. Neurocomputing 323:37\u201351","journal-title":"Neurocomputing"},{"key":"10213_CR224","doi-asserted-by":"crossref","unstructured":"Zhang T, Cheng H-P, Li Z, Yan F, Huang C, Li H, Chen Y (2020) Autoshrink: a topology-aware NAS for discovering efficient neural architecture. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 6829\u20136836","DOI":"10.1609\/aaai.v34i04.6163"},{"key":"10213_CR225","doi-asserted-by":"crossref","unstructured":"Zhang Z, Lu X, Cao G, Yang Y, Jiao L, Liu F (2021a) Vit-yolo: Transformer-based yolo for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2799\u20132808","DOI":"10.1109\/ICCVW54120.2021.00314"},{"key":"10213_CR226","doi-asserted-by":"crossref","unstructured":"Zhang C, Yuan G, Niu W, Tian J, Jin S, Zhuang D, Jiang Z, Wang Y, Ren B, Song SL et\u00a0al (2021b) Clicktrain: efficient and accurate end-to-end deep learning training via fine-grained architecture-preserving pruning. In: Proceedings of the ACM international conference on supercomputing, pp 266\u2013278","DOI":"10.1145\/3447818.3459988"},{"key":"10213_CR229","doi-asserted-by":"crossref","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2019) M2det: a single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 9259\u20139266","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"10213_CR227","doi-asserted-by":"crossref","unstructured":"Zhao T, Cao K, Yao J, Nogues I, Lu L, Huang L, Xiao J, Yin Z, Zhang L (2021a) 3D graph anatomy geometry-integrated network for pancreatic mass segmentation, diagnosis, and quantitative patient management. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13743\u201313752","DOI":"10.1109\/CVPR46437.2021.01353"},{"key":"10213_CR228","doi-asserted-by":"crossref","unstructured":"Zhao H, Zhou W, Chen D, Wei T, Zhang W, Yu N (2021b) Multi-attentional deepfake detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2185\u20132194","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"10213_CR230","doi-asserted-by":"crossref","unstructured":"Zhong Z, Yang Z, Deng B, Yan J, Wu W, Shao J, Liu C-L (2020) Blockqnn: efficient block-wise neural network architecture generation. IEEE Trans Pattern Anal Mach Intell 43(7):2314\u20132328","DOI":"10.1109\/TPAMI.2020.2969193"},{"key":"10213_CR232","doi-asserted-by":"crossref","unstructured":"Zhou H, Alvarez JM, Porikli F (2016) Less is more: towards compact CNNs. In: European conference on computer vision. Springer, Berlin, pp 662\u2013677","DOI":"10.1007\/978-3-319-46493-0_40"},{"key":"10213_CR231","first-page":"12","volume":"73","author":"M Zhou","year":"2019","unstructured":"Zhou M, Liu Y, Long Z, Chen L, Zhu C (2019) Tensor rank learning in CP decomposition via convolutional neural network. Signal Process Image Commun 73:12\u201321","journal-title":"Signal Processing: Image Communication"},{"key":"10213_CR233","doi-asserted-by":"crossref","unstructured":"Zhou S, Wang Y, Chen D, Chen J, Wang X, Wang C, Bu J (2021) Distilling holistic knowledge with graph neural networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10387\u201310396","DOI":"10.1109\/ICCV48922.2021.01022"},{"key":"10213_CR234","unstructured":"Zhou S, Wu Y, Ni Z, Zhou X, Wen H, Zou Y (2016) DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint. arXiv:2004.10934"},{"key":"10213_CR235","unstructured":"Zhu C, Han S, Mao H, Dally WJ (2016) Trained ternary quantization. arXiv preprint. arXiv:1612.01064"},{"key":"10213_CR236","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, Zhao Q (2021a) TPH-YOLOv5: improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2778\u20132788","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"10213_CR237","doi-asserted-by":"crossref","unstructured":"Zhu J, Tang S, Chen D, Yu S, Liu Y, Rong M, Yang A, Wang X (2021b) Complementary relation contrastive distillation. In: Proceedings of the IEEE\/CVF international conference on computer visionand pattern recognition, pp 9260\u20139269","DOI":"10.1109\/CVPR46437.2021.00914"},{"key":"10213_CR238","unstructured":"Zoph B, Le QV (2016) Neural architecture search with reinforcement learning. arXiv preprint. arXiv:1611.01578"},{"key":"10213_CR239","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-022-10213-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-022-10213-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-022-10213-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T08:34:24Z","timestamp":1676622864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-022-10213-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,22]]},"references-count":239,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["10213"],"URL":"https:\/\/doi.org\/10.1007\/s10462-022-10213-5","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,22]]},"assertion":[{"value":"22 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}