{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:25:50Z","timestamp":1760711150668,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T00:00:00Z","timestamp":1680739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T00:00:00Z","timestamp":1680739200000},"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":["J Supercomput"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s11227-023-05212-4","type":"journal-article","created":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T17:02:42Z","timestamp":1680800562000},"page":"14313-14341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["LOCP: Latency-optimized channel pruning for CNN inference acceleration on GPUs"],"prefix":"10.1007","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6018-0379","authenticated-orcid":false,"given":"Yonghua","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuting","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runhua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongxiang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,6]]},"reference":[{"key":"5212_CR1","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2020.01.085","volume":"396","author":"X Wu","year":"2020","unstructured":"Wu X, Sahoo D, Hoi SCH (2020) Recent advances in deep learning for object detection. Neurocomputing 396:39\u201364","journal-title":"Neurocomputing"},{"key":"5212_CR2","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/OJSP.2020.3045349","volume":"2","author":"P Bell","year":"2020","unstructured":"Bell P, Fainberg J, Klejch O et al (2020) Adaptation algorithms for neural network-based speech recognition: an overview. IEEE Open J Signal Process 2:33\u201366","journal-title":"IEEE Open J Signal Process"},{"issue":"7","key":"5212_CR3","first-page":"3523","volume":"44","author":"S Minaee","year":"2021","unstructured":"Minaee S, Boykov YY, Porikli F et al (2021) Image segmentation using deep learning: a survey. IEEE Trans Pattern Anal Mach Intell 44(7):3523\u20133542","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"5212_CR4","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1049\/itr2.12088","volume":"15","author":"L Hu","year":"2021","unstructured":"Hu L, Zhou X, Zhang X et al (2021) A review on key challenges in intelligent vehicles: safety and driver-oriented features. IET Intel Transport Syst 15(9):1093\u20131105","journal-title":"IET Intel Transport Syst"},{"issue":"6","key":"5212_CR5","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"5212_CR6","unstructured":"Tan M, Le Q. (2021) Efficientnetv2: Smaller models and faster training In: International Conference on Machine Learning. PMLR, pp 10096\u201310106."},{"issue":"10","key":"5212_CR7","doi-asserted-by":"publisher","first-page":"6140","DOI":"10.1109\/TPAMI.2021.3088904","volume":"44","author":"B Zhuang","year":"2021","unstructured":"Zhuang B, Tan M, Liu J et al (2021) Effective training of convolutional neural networks with low-bitwidth weights and activations. IEEE Trans Pattern Anal Mach Intell 44(10):6140\u20136152","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5212_CR8","doi-asserted-by":"crossref","unstructured":"Yang C, Xie L, Su C, et al. (2019) Snapshot distillation: Teacher-student optimization in one generation In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 2859\u20132868.","DOI":"10.1109\/CVPR.2019.00297"},{"key":"5212_CR9","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":"5212_CR10","doi-asserted-by":"crossref","unstructured":"Lin M, Ji R, Zhang Y, et al. (2021) Channel pruning via automatic structure search In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. pp 673\u2013679.","DOI":"10.24963\/ijcai.2020\/94"},{"key":"5212_CR11","doi-asserted-by":"crossref","unstructured":"Tu C H, Lee J H, Chan Y M, et al. (2020) Pruning depthwise separable convolutions for mobilenet compression In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1\u20138.","DOI":"10.1109\/IJCNN48605.2020.9207259"},{"key":"5212_CR12","unstructured":"Lubana E S, Dick R. (2020) A Gradient Flow Framework For Analyzing Network Pruning In: International Conference on Learning Representations."},{"key":"5212_CR13","doi-asserted-by":"crossref","unstructured":"Li Y, Gu S, Mayer C, et al. (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":"5212_CR14","doi-asserted-by":"crossref","unstructured":"Radu V, Kaszyk K, Wen Y, et al. (2019) Performance aware convolutional neural network channel pruning for embedded GPUs In: 2019 IEEE International Symposium on Workload Characterization (IISWC). IEEE, pp 24\u201334.","DOI":"10.1109\/IISWC47752.2019.9042000"},{"key":"5212_CR15","unstructured":"Molchanov P, Tyree S, Karras T, et al. (2017) Pruning convolutional neural networks for resource efficient inference In: International Conference on Learning Representations, ICLR 2017-Conference Track Proceedings."},{"key":"5212_CR16","unstructured":"Wang C, Zhang G, Grosse R. (2020) Picking Winning Tickets Before Training by Preserving Gradient Flow In: International Conference on Learning Representations, ICLR 2020-Conference Track Proceedings."},{"key":"5212_CR17","unstructured":"Yu J, Huang T. Autoslim: Towards one-shot architecture search for channel numbers. arXiv preprint arXiv:1903.11728, 2019."},{"key":"5212_CR18","first-page":"639","volume-title":"European Conference on Computer Vision","author":"B Li","year":"2020","unstructured":"Li B, Wu B, Su J et al (2020) Eagleeye: Fast sub-net evaluation for efficient neural network pruning. In: European Conference on Computer Vision. Springer, Cham, pp 639\u2013654"},{"key":"5212_CR19","doi-asserted-by":"crossref","unstructured":"Wu Y C, Liu C T, Chen B Y, et al. 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":"5212_CR20","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"},{"issue":"1","key":"5212_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2021.100009","volume":"1","author":"J Liu","year":"2021","unstructured":"Liu J, Sun J, Xu Z et al (2021) Latency-aware automatic CNN channel pruning with GPU runtime analysis. BenchCouncil Trans Benchmarks, Stand Eval 1(1):100009","journal-title":"BenchCouncil Trans Benchmarks, Stand Eval"},{"key":"5212_CR22","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":"5212_CR23","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":"5212_CR24","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":"5212_CR25","doi-asserted-by":"crossref","unstructured":"Chen C, Tung F, Vedula N, et al. (2018) Constraint-aware deep neural network compression In: Proceedings of the European Conference on Computer Vision (ECCV). pp 400\u2013415.","DOI":"10.1007\/978-3-030-01237-3_25"},{"key":"5212_CR26","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":"5212_CR27","unstructured":"Denton E L, Zaremba W, Bruna J, et al. (2014) Exploiting linear structure within convolutional networks for efficient evaluation. Advances in neural information processing systems, pp 27."},{"key":"5212_CR28","unstructured":"Ba J, Caruana R. Do deep nets really need to be deep?[J]. Advances in neural information processing systems, 2014, 27."},{"key":"5212_CR29","unstructured":"Li H, Kadav A, Durdanovic I, et al. (2017) Pruning filters for efficient convnets, In: International Conference on Learning Representations."},{"key":"5212_CR30","unstructured":"Molchanov P, Tyree S, Karras T, et al. (2017) Pruning convolutional neural networks for resource efficient inference[C]\/\/International Conference on Learning Representations."},{"issue":"4","key":"5212_CR31","doi-asserted-by":"publisher","first-page":"1232","DOI":"10.1109\/TCSI.2019.2958937","volume":"67","author":"Z Chen","year":"2020","unstructured":"Chen Z, Chen Z, Lin J et al (2020) Deep neural network acceleration based on low-rank approximated channel pruning[J]. IEEE Trans Circuits Syst I Regul Pap 67(4):1232\u20131244","journal-title":"IEEE Trans Circuits Syst I Regul Pap"},{"key":"5212_CR32","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":"5212_CR33","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":"5212_CR34","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":"5212_CR35","unstructured":"Wen W, Wu C, Wang Y, et al. (2016) Learning structured sparsity in deep neural networks. Advances in neural information processing systems, pp 29."},{"key":"5212_CR36","unstructured":"Louizos C, Welling M, Kingma D P. (2018) Learning sparse neural networks through L_0 Regularization In: International Conference on Learning Representations."},{"issue":"4","key":"5212_CR37","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/JSTSP.2020.2971418","volume":"14","author":"C Gamanayake","year":"2020","unstructured":"Gamanayake C, Jayasinghe L, Ng BKK et al (2020) Cluster pruning: an efficient filter pruning method for edge ai vision applications. IEEE J Sel Top Signal Process 14(4):802\u2013816","journal-title":"IEEE J Sel Top Signal Process"},{"key":"5212_CR38","unstructured":"Yu F, Xu Z, Shen T, et al. (2020) Towards latency-aware dnn optimization with gpu runtime analysis and tail effect elimination. arXiv preprint arXiv:2011.03897"},{"key":"5212_CR39","unstructured":"Shen M, Yin H, Molchanov P, et al. (2021) HALP: Hardware-Aware Latency Pruning. arXiv preprint arXiv:2110.10811"},{"key":"5212_CR40","doi-asserted-by":"crossref","unstructured":"Yu F, Han C, Wang P, et al. (2021) HFP: Hardware-Aware Filter Pruning for Deep Convolutional Neural Networks Acceleration In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, pp 255\u2013262.","DOI":"10.1109\/ICPR48806.2021.9412294"},{"key":"5212_CR41","unstructured":"Paszke A, Gross S and et al. (2019) Pytorch: an imperative style, high-performance deep learning library. Advances in neural information processing systems, pp 32."},{"key":"5212_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102431","volume":"124","author":"G Li","year":"2022","unstructured":"Li G, Ma X, Wang X et al (2022) Optimizing deep neural networks on intelli-gent edge accelerators via flexible-rate filter pruning. J Syst Archit 124:102431","journal-title":"J Syst Archit"},{"key":"5212_CR43","unstructured":"Zhu L (2018) THOP: PyTorch-OpCounter. https:\/\/pypi.org\/project\/thop\/"},{"key":"5212_CR44","unstructured":"Krizhevsky A, Hinton G. (2009) Learning multiple layers of features from tiny images."},{"key":"5212_CR45","unstructured":"Le Y, Yang X. 2015 Tiny imagenet visual recognition challenge. CS 231N, 7(7): 3"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05212-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05212-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05212-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T11:09:13Z","timestamp":1687864153000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05212-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,6]]},"references-count":45,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["5212"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05212-4","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2023,4,6]]},"assertion":[{"value":"18 March 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2023","order":2,"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 conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}