{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:40:56Z","timestamp":1762508456888,"version":"3.41.2"},"reference-count":40,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":108,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY19F020027"],"award-info":[{"award-number":["LY19F020027"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Many current convolutional neural networks are hard to meet the practical application requirement because of the enormous network parameters. For accelerating the inference speed of networks, more and more attention has been paid to network compression. Network pruning is one of the most efficient and simplest ways to compress and speed up the networks. In this paper, a pruning algorithm for the lightweight task is proposed, and a pruning strategy based on feature representation is investigated. Different from other pruning approaches, the proposed strategy is guided by the practical task and eliminates the irrelevant filters in the network. After pruning, the network is compacted to a smaller size and is easy to recover accuracy with fine\u2010tuning. The performance of the proposed pruning algorithm is validated on the acknowledged image datasets, and the experimental results prove that the proposed algorithm is more suitable to prune the irrelevant filters for the fine\u2010tuning dataset.<\/jats:p>","DOI":"10.1155\/2021\/5531023","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T16:47:46Z","timestamp":1618850866000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Small Network for Lightweight Task in Computer Vision: A Pruning Method Based on Feature Representation"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7620-5120","authenticated-orcid":false,"given":"Yisu","family":"Ge","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8711-1605","authenticated-orcid":false,"given":"Shufang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1209-0608","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"e_1_2_10_1_2","unstructured":"DenilM. ShakibiB. DinhL. andDe FreitasN. Predicting parameters in deep learning Proceedings of the Advances in Neural Information Processing Systems December 2013 Lake Tahoe NV USA 2148\u20132156."},{"key":"e_1_2_10_2_2","doi-asserted-by":"crossref","unstructured":"GirshickR. DonahueJ. DarrellT. andMalikJ. Rich feature hierarchies for accurate object detection and semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2014 Columbus OH USA 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_10_3_2","doi-asserted-by":"crossref","unstructured":"GirshickR. Fast r-cnn Proceedings of the IEEE International Conference on Computer Vision December 2015 Santiago Chile 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_10_4_2","unstructured":"RenS. HeK. GirshickR. andSunJ. Faster r-cnn: towards real-time object detection with region proposal networks Proceedings of the Advances in Neural Information Processing Systems November 2015 Istanbul Turkey 91\u201399."},{"key":"e_1_2_10_5_2","unstructured":"HowardA. G. ZhuM. ChenB.et al. Efficient convolutional neural networks for mobile vision applications 2017 http:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"SandlerM. HowardA. ZhuM. ZhmoginovA. andChenL.-C. Mobilenetv2: inverted residuals and linear bottlenecks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"ZhangT. QiG. J. XiaoB. andWangJ. Interleaved group convolutions Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy.","DOI":"10.1109\/ICCV.2017.469"},{"key":"e_1_2_10_8_2","doi-asserted-by":"crossref","unstructured":"XieG. WangJ. ZhangT. LaiJ. HongR. andQiG.-J. Interleaved structured sparse convolutional neural networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 8847\u20138856.","DOI":"10.1109\/CVPR.2018.00922"},{"key":"e_1_2_10_9_2","unstructured":"SunK. LiM. LiuD. andWangJ. Igcv3: interleaved low-rank group convolutions for efficient deep neural networks 2018 http:\/\/arxiv.org\/abs\/1806.00178."},{"key":"e_1_2_10_10_2","unstructured":"ChoiY. El-KhamyM. andLeeJ. Towards the limit of network quantization Proceedings of the International Conference on Learning Representations April 2017 Toulon France."},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_40"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"PengB. TanW. LiZ. ZhangS. XieD. andPuS. Extreme network compression via filter group approximation Proceedings of the European Conference on Computer Vision (ECCV) September 2018 Munich Germany 300\u2013316.","DOI":"10.1007\/978-3-030-01237-3_19"},{"key":"e_1_2_10_13_2","unstructured":"CourbariauxM. BengioY. andDavidJ.-P. Binaryconnect: training deep neural networks with binary weights during propagations Proceedings of the Advances in Neural Information Processing Systems November 2015 Istanbul Turkey 3123\u20133131."},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"RastegariM. OrdonezV. RedmonJ. andFarhadiA. Xnor-net: imagenet classification using binary convolutional neural networks Proceedings of the European Conference on Computer Vision October 2016 Amsterdam Netherlands Springer 525\u2013542.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_2_10_15_2","unstructured":"HintonG. VinyalsO. andDeanJ. Distilling the knowledge in a neural network Proceedings of the Advances in Neural Information Processing Systems November 2015 Istanbul Turkey."},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"YimJ. JooD. BaeJ. andKimJ. A gift from knowledge distillation: fast optimization network minimization and transfer learning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA 4133\u20134141.","DOI":"10.1109\/CVPR.2017.754"},{"key":"e_1_2_10_17_2","unstructured":"ZagoruykoS.andKomodakisN. Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer Proceedings of the International Conference on Learning Representations April 2017 Toulon France."},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"HeoB. LeeM. YunS. andJinY. C. Improving knowledge distillation with supporting adversarial samples Proceedings of the Thirty-Third AAAI Conference on Articial Intelligence February 2019 Honolulu HI USA.","DOI":"10.1609\/aaai.v33i01.33013771"},{"key":"e_1_2_10_19_2","unstructured":"HanS. MaoH. andDallyW. J. Deep compression: compressing deep neural networks with pruning trained quantization and human coding Proceedings of the International Conference on Learning Representations May 2016 San Juan Puerto Rico."},{"key":"e_1_2_10_20_2","unstructured":"LiH. KadavA. DurdanovicI. SametH. andGrafH. P. Pruning filters for efficient convnets Proceedings of the International Conference on Learning Representations April 2017 Toulon France."},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","unstructured":"HeY. ZhangX. andSunJ. Channel pruning for accelerating very deep neural networks Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 1389\u20131397.","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_2_10_22_2","doi-asserted-by":"crossref","unstructured":"YuR. LiA. ChenC.-F.et al. Nisp: pruning networks using neuron importance score propagation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 9194\u20139203.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"e_1_2_10_23_2","doi-asserted-by":"crossref","unstructured":"MolchanovP. MallyaA. TyreeS. FrosioI. andKautzJ. Importance estimation for neural network pruning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 11264\u201311272.","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_2_10_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"SunY. WangX. andTangX. Sparsifying neural network connections for face recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA 4856\u20134864.","DOI":"10.1109\/CVPR.2016.525"},{"key":"e_1_2_10_26_2","doi-asserted-by":"crossref","unstructured":"SrinivasS.andBabuR. V. Data-free parameter pruning for deep neural networks Proceedings of the British Machine Vision Conference September 2015 Swansea UK.","DOI":"10.5244\/C.29.31"},{"key":"e_1_2_10_27_2","doi-asserted-by":"crossref","unstructured":"DingX. DingG. GuoY. andHanJ. Centripetal sgd for pruning very deep convolutional networks with complicated structure Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 4943\u20134953.","DOI":"10.1109\/CVPR.2019.00508"},{"key":"e_1_2_10_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"e_1_2_10_29_2","doi-asserted-by":"crossref","unstructured":"MallyaA.andLazebnikS. Packnet: adding multiple tasks to a single network by iterative pruning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 7765\u20137773.","DOI":"10.1109\/CVPR.2018.00810"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"YangM. FarajM. HusseinA. andGaudetV. Efficient hardware realization of convolutional neural networks using intra-kernel regular pruning Proceedings of the 2018 IEEE 48th International Symposium on Multiple-Valued Logic (ISMVL) May 2018 Linz Austria IEEE 180\u2013185.","DOI":"10.1109\/ISMVL.2018.00039"},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"GhoshS. SrinivasaS. K. K. AmonP. HutterA. andKaupA. Deep network pruning for object detection Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP) September 2019 Taipei Taiwan IEEE 3915\u20133919.","DOI":"10.1109\/ICIP.2019.8803505"},{"key":"e_1_2_10_32_2","unstructured":"LiuZ. SunM. ZhouT. HuangG. andDarrellT. Rethinking the value of network pruning Proceedings of the International Conference on Learning Representations May 2019 New Orleans LA USA."},{"key":"e_1_2_10_33_2","unstructured":"FrankleJ.andCarbinM. The lottery ticket hypothesis: finding sparse trainable neural networks Proceedings of the International Conference on Learning Representations May 2019 New Orleans LA USA."},{"key":"e_1_2_10_34_2","unstructured":"JiaY. ShelhamerE. DonahueJ.et al. Convolutional architecture for fast feature embedding Proceedings of the 22nd ACM International Conference on Multimedia June 2014 Mountain View CA USA 675\u2013678."},{"key":"e_1_2_10_35_2","unstructured":"SimonyanK.andZissermanA. Very deep convolutional networks for large-scale image recognition 2014 http:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_2_10_36_2","unstructured":"RedmonJ.andFarhadiA. Yolov3: an incremental improvement 2018 http:\/\/arxiv.org\/abs\/1804.02767."},{"key":"e_1_2_10_37_2","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"Krizhevsky A.","year":"2009","journal-title":"Handbook of Systemic Autoimmune Diseases"},{"key":"e_1_2_10_38_2","unstructured":"DengJ. DongW. SocherR.et al. A large-scale hierarchical image database Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition June 2009 Miami FL USA 248\u2013255."},{"key":"e_1_2_10_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_2_10_40_2","doi-asserted-by":"crossref","unstructured":"LiuZ. LiJ. ShenZ. HuangG. YanS. andZhangC. Learning efficient convolutional networks through network slimming Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 2736\u20132744.","DOI":"10.1109\/ICCV.2017.298"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5531023.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5531023.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5531023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:36:31Z","timestamp":1722947791000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5531023"}},"subtitle":[],"editor":[{"given":"Paolo","family":"Gastaldo","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5531023"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5531023","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-02-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5531023"}}