{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T20:46:12Z","timestamp":1770497172499,"version":"3.49.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T00:00:00Z","timestamp":1709596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T00:00:00Z","timestamp":1709596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s00521-024-09539-8","type":"journal-article","created":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T14:02:41Z","timestamp":1709647361000},"page":"8825-8842","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["HILP: hardware-in-loop pruning of convolutional neural networks towards inference acceleration"],"prefix":"10.1007","volume":"36","author":[{"given":"Dong","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianqian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyue","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunda","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,5]]},"reference":[{"key":"9539_CR1","unstructured":"Howard AG, Zhu M, Chen B, et al (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"9539_CR2","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"9539_CR3","unstructured":"LeCun Y, Denker J, Solla S (1989) Optimal brain damage. Advances in neural information processing systems 2"},{"key":"9539_CR4","unstructured":"Hassibi B, Stork D (1992) Second order derivatives for network pruning: optimal brain surgeon. Advances in neural information processing systems 5"},{"key":"9539_CR5","unstructured":"Li H, Kadav A, Durdanovic I, et al (2016) Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710"},{"key":"9539_CR6","unstructured":"Courbariaux M, Bengio Y, David J-P (2015) Binaryconnect: Training deep neural networks with binary weights during propagations. Advances in neural information processing systems 28"},{"issue":"1","key":"9539_CR7","first-page":"6869","volume":"18","author":"I Hubara","year":"2017","unstructured":"Hubara I, Courbariaux M, Soudry D et al (2017) Quantized neural networks: training neural networks with low precision weights and activations. J Mach Learn Res 18(1):6869\u20136898","journal-title":"J Mach Learn Res"},{"key":"9539_CR8","unstructured":"Denton EL, Zaremba W, Bruna J, et al (2014) Exploiting linear structure within convolutional networks for efficient evaluation. Advances in neural information processing systems 27"},{"key":"9539_CR9","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 2(7)"},{"key":"9539_CR10","unstructured":"Han S, Pool J, Tran J, Dally W (2015) Learning both weights and connections for efficient neural network. Advances in neural information processing systems 28"},{"key":"9539_CR11","doi-asserted-by":"crossref","unstructured":"Srinivas S, Babu RV (2015) Data-free parameter pruning for deep neural networks. arXiv preprint arXiv:1507.06149","DOI":"10.5244\/C.29.31"},{"issue":"3","key":"9539_CR12","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1145\/3007787.3001163","volume":"44","author":"S Han","year":"2016","unstructured":"Han S, Liu X, Mao H et al (2016) Eie: efficient inference engine on compressed deep neural network. ACM SIGARCH Comput Archit News 44(3):243\u2013254","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"9539_CR13","unstructured":"Park J, Li S, Wen W, et al (2016) Faster CNNS with direct sparse convolutions and guided pruning. arXiv preprint arXiv:1608.01409"},{"key":"9539_CR14","first-page":"24604","volume":"34","author":"Y Sui","year":"2021","unstructured":"Sui Y, Yin M, Xie Y et al (2021) Chip: channel independence-based pruning for compact neural networks. Adv Neural Inf Process Syst 34:24604\u201324616","journal-title":"Adv Neural Inf Process Syst"},{"key":"9539_CR15","doi-asserted-by":"crossref","unstructured":"Lin S, Ji R, Yan C, et al (2019) Towards optimal structured cnn pruning via generative adversarial learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2790\u20132799","DOI":"10.1109\/CVPR.2019.00290"},{"key":"9539_CR16","unstructured":"You Z, Yan K, Ye J, et al (2019) Gate decorator: global filter pruning method for accelerating deep convolutional neural networks. Advances in neural information processing systems 32"},{"key":"9539_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3259402","author":"M Lin","year":"2023","unstructured":"Lin M, Chen B, Chao F, Ji R (2023) Training compact CNNS for image classification using dynamic-coded filter fusion. IEEE Trans Patt Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2023.3259402","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"9539_CR18","doi-asserted-by":"crossref","unstructured":"He Y, Liu P, Wang Z, et al (2019) Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4340\u20134349","DOI":"10.1109\/CVPR.2019.00447"},{"key":"9539_CR19","unstructured":"Molchanov P, Tyree S, Karras T, et al (2016) Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440"},{"key":"9539_CR20","doi-asserted-by":"crossref","unstructured":"Li D, Chen S, Liu X, et al (2020) Towards optimal filter pruning with balanced performance and pruning speed. In: Proceedings of the Asian conference on computer vision","DOI":"10.1007\/978-3-030-69538-5_16"},{"key":"9539_CR21","doi-asserted-by":"crossref","unstructured":"Lin M, Ji R, Wang Y, et al (2020) Hrank: filter pruning using high-rank feature map. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1529\u20131538","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"9539_CR22","doi-asserted-by":"crossref","unstructured":"Lin M, Ji R, Zhang Y, et al (2020) Channel pruning via automatic structure search. arXiv preprint arXiv:2001.08565","DOI":"10.24963\/ijcai.2020\/94"},{"key":"9539_CR23","doi-asserted-by":"crossref","unstructured":"Liu Z, Li J, Shen Z, et al (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":"9539_CR24","doi-asserted-by":"crossref","unstructured":"Li B, Wu B, Su J, Wang G (2020) Eagleeye: Fast sub-net evaluation for efficient neural network pruning. In: European conference on computer vision, pp. 639\u2013654","DOI":"10.1007\/978-3-030-58536-5_38"},{"key":"9539_CR25","doi-asserted-by":"crossref","unstructured":"He Y, Lin J, Liu Z, et al (2018) Amc: Automl for model compression and acceleration on mobile devices. In: Proceedings of the European conference on computer vision, pp. 784\u2013800","DOI":"10.1007\/978-3-030-01234-2_48"},{"issue":"11","key":"9539_CR26","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2996864","volume":"59","author":"Y Chen","year":"2016","unstructured":"Chen Y, Chen T, Xu Z et al (2016) Diannao family: energy-efficient hardware accelerators for machine learning. Commun ACM 59(11):105\u2013112","journal-title":"Commun ACM"},{"key":"9539_CR27","doi-asserted-by":"crossref","unstructured":"Wu Y-C, Liu C-T, Chen B-Y, Chien S-Y (2020) Constraint-aware importance estimation for global filter pruning under multiple resource constraints. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp. 686\u2013687","DOI":"10.1109\/CVPRW50498.2020.00351"},{"key":"9539_CR28","doi-asserted-by":"crossref","unstructured":"Yang T-J, Howard A, Chen B, et al (2018) Netadapt: Platform-aware neural network adaptation for mobile applications. In: Proceedings of the European conference on computer vision (ECCV), pp. 285\u2013300","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"9539_CR29","unstructured":"Shen M, Yin H, Molchanov P, et al (2021) Halp: hardware-aware latency pruning. arXiv preprint arXiv:2110.10811"},{"key":"9539_CR30","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.neunet.2022.05.002","volume":"152","author":"Z Chen","year":"2022","unstructured":"Chen Z, Liu C, Yang W et al (2022) Lap: latency-aware automated pruning with dynamic-based filter selection. Neural Netw 152:407\u2013418","journal-title":"Neural Netw"},{"issue":"1","key":"9539_CR31","doi-asserted-by":"publisher","first-page":"100009","DOI":"10.1016\/j.tbench.2021.100009","volume":"1","author":"J Liu","year":"2021","unstructured":"Liu J, Sun J, Xu Z, Sun G (2021) Latency-aware automatic CNN channel pruning with GPU runtime analysis. BenchCouncil Trans Benchmk, Stand Eval 1(1):100009","journal-title":"BenchCouncil Trans Benchmk, Stand Eval"},{"key":"9539_CR32","doi-asserted-by":"crossref","unstructured":"Dong J-D, Cheng A-C, Juan D-C, et al (2018) Dpp-net: device-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":"9539_CR33","doi-asserted-by":"crossref","unstructured":"Dai X, Zhang P, Wu B, et al (2019) Chamnet: towards efficient network design through platform-aware model adaptation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11398\u201311407","DOI":"10.1109\/CVPR.2019.01166"},{"key":"9539_CR34","doi-asserted-by":"crossref","unstructured":"Wu B, Dai X, Zhang P, et al (2019) Fbnet: hardware-aware efficient convnet design via differentiable neural architecture search. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10734\u201310742","DOI":"10.1109\/CVPR.2019.01099"},{"key":"9539_CR35","doi-asserted-by":"crossref","unstructured":"Yang T-J, Liao Y-L, Sze V (2021) Netadaptv2: efficient neural architecture search with fast super-network training and architecture optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2402\u20132411","DOI":"10.1109\/CVPR46437.2021.00243"},{"key":"9539_CR36","doi-asserted-by":"crossref","unstructured":"Zhang P, Zhong Y, Li X (2019) Slimyolov3: narrower, faster and better for real-time UAV applications. In: Proceedings of the IEEE\/CVF International conference on computer vision workshops","DOI":"10.1109\/ICCVW.2019.00011"},{"key":"9539_CR37","doi-asserted-by":"crossref","unstructured":"Tan M, Chen B, Pang R, et al (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":"9539_CR38","unstructured":"Cai H, Gan C, Wang T, et al (2019) Once-for-all: train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791"},{"key":"9539_CR39","doi-asserted-by":"crossref","unstructured":"Abbasi S, Wong A, Shafiee MJ (2022) Maple: microprocessor a priori for latency estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2747\u20132756","DOI":"10.1109\/CVPRW56347.2022.00310"},{"key":"9539_CR40","first-page":"2","volume":"1","author":"H Vanholder","year":"2016","unstructured":"Vanholder H (2016) Efficient inference with tensorrt. GPU Technol Conf 1:2","journal-title":"GPU Technol Conf"},{"key":"9539_CR41","doi-asserted-by":"crossref","unstructured":"Liu S, Du Z, Tao J, et al (2016) Cambricon: An instruction set architecture for neural networks. In: 2016 ACM\/IEEE 43rd Annual international symposium on computer architecture (ISCA), pp. 393\u2013405","DOI":"10.1109\/ISCA.2016.42"},{"key":"9539_CR42","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":"9539_CR43","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"9539_CR44","doi-asserted-by":"crossref","unstructured":"Molchanov P, Mallya A, Tyree S, et al (2019) Importance estimation for neural network pruning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11264\u201311272","DOI":"10.1109\/CVPR.2019.01152"},{"key":"9539_CR45","unstructured":"Hu H, Peng R, Tai Y-W, Tang C-K (2016) Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250"},{"key":"9539_CR46","doi-asserted-by":"crossref","unstructured":"Yu R, Li A, Chen C-F, et al (2018) Nisp: pruning networks using neuron importance score propagation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 9194\u20139203","DOI":"10.1109\/CVPR.2018.00958"},{"key":"9539_CR47","doi-asserted-by":"crossref","unstructured":"Lin S, Ji R, Li Y, et al (2018) Accelerating convolutional networks via global and dynamic filter pruning. In: Proceedings of the 27th international joint conference on artificial intelligence, pp. 2425\u20132432","DOI":"10.24963\/ijcai.2018\/336"},{"key":"9539_CR48","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"},{"key":"9539_CR49","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":"9539_CR50","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang N (2018) Data-driven sparse structure selection for deep neural networks. In: Proceedings of the European conference on computer vision, pp. 304\u2013320","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"9539_CR51","doi-asserted-by":"crossref","unstructured":"Ding X, Ding G, Guo Y, Han J (2019) Centripetal sgd for pruning very deep convolutional networks with complicated structure. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4943\u20134953","DOI":"10.1109\/CVPR.2019.00508"},{"key":"9539_CR52","doi-asserted-by":"crossref","unstructured":"Liu Z, Mu H, Zhang X, et al (2019) Metapruning: meta learning for automatic neural network channel pruning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3296\u20133305","DOI":"10.1109\/ICCV.2019.00339"},{"key":"9539_CR53","unstructured":"Zoph B, Le QV (2016) Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578"},{"key":"9539_CR54","unstructured":"Liu H, Simonyan K, Yang Y (2018) Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055"},{"key":"9539_CR55","doi-asserted-by":"crossref","unstructured":"Elkerdawy S, Elhoushi M, Singh A, et al (2020) To filter prune, or to layer prune, that is the question. In: Proceedings of the Asian conference on computer vision","DOI":"10.1007\/978-3-030-69535-4_45"},{"key":"9539_CR56","unstructured":"Cai H, Zhu L, Han S (2018) Proxylessnas: direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332"},{"key":"9539_CR57","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"9539_CR58","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images"},{"key":"9539_CR59","unstructured":"de Jorge P, Sanyal A, Behl HS, et al (2020) Progressive skeletonization: trimming more fat from a network at initialization. arXiv preprint arXiv:2006.09081"},{"key":"9539_CR60","unstructured":"Verdenius S, Stol M, Forr\u00e9 P (2020) Pruning via iterative ranking of sensitivity statistics. arXiv preprint arXiv:2006.00896"},{"key":"9539_CR61","unstructured":"Chetlur S, Woolley C, Vandermersch P, et al (2014) cudnn: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759"},{"issue":"3","key":"9539_CR62","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211\u2013252","journal-title":"Int J Comput Vision"},{"key":"9539_CR63","unstructured":"Paszke A, Gross S, Massa F, et al (2019) Pytorch: an imperative style, high-performance deep earning library. Advances in neural information processing systems 32"},{"key":"9539_CR64","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, et al (2014) Microsoft coco: common objects in context. In: European conference on computer vision, pp. 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"9539_CR65","doi-asserted-by":"crossref","unstructured":"Zhang J, Wang P, Zhao Z, Su F (2021) Pruned-yolo: learning efficient object detector using model pruning. In: International conference on artificial neural networks, pp. 34\u201345","DOI":"10.1007\/978-3-030-86380-7_4"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09539-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-09539-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09539-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T21:11:35Z","timestamp":1731532295000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-09539-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,5]]},"references-count":65,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["9539"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-09539-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,5]]},"assertion":[{"value":"23 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}