{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T08:02:07Z","timestamp":1767168127447,"version":"build-2238731810"},"reference-count":43,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"content-version":"vor","delay-in-days":360,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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>In the real\u2010world scenario, data often have a long\u2010tailed distribution and training deep neural networks on such an imbalanced dataset has become a great challenge. The main problem caused by a long\u2010tailed data distribution is that common classes will dominate the training results and achieve a very low accuracy on the rare classes. Recent work focuses on improving the network representation ability to overcome the long\u2010tailed problem, while it always ignores adapting the network classifier to a long\u2010tailed case, which will cause the \u201cincompatibility\u201d problem of network representation and network classifier. In this paper, we use knowledge distillation to solve the long\u2010tailed data distribution problem and fully optimize the network representation and classifier simultaneously. We propose multiexperts knowledge distillation with class\u2010balanced sampling to jointly learn high\u2010quality network representation and classifier. Also, a channel activation\u2010based knowledge distillation method is also proposed to improve the performance further. State\u2010of\u2010the\u2010art performance on several large\u2010scale long\u2010tailed classification datasets shows the superior generalization of our method.<\/jats:p>","DOI":"10.1155\/2021\/6702625","type":"journal-article","created":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T14:22:32Z","timestamp":1640614952000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["[Retracted] Relieving the Incompatibility of Network Representation and Classification for Long\u2010Tailed Data Distribution"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9422-750X","authenticated-orcid":false,"given":"Hao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-6005","authenticated-orcid":false,"given":"Mengya","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1374-0684","authenticated-orcid":false,"given":"Mingsheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,12,27]]},"reference":[{"key":"e_1_2_9_1_2","unstructured":"KrizhevskyA.andHintonG. Learning Multiple Layers of Features from Tiny Images. 2009."},{"key":"e_1_2_9_2_2","doi-asserted-by":"crossref","unstructured":"JiaD. DongW. SocherR. LiLi-J. LiK. andFei-FeiLi ImageNet: 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.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2767"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"KordestaniM. SamadiM. F. andSaifM. A distributed fault detection and isolation method for multifunctional spoiler system Proceedings of the 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS) August 2018 Windsor Canada 380\u2013383 https:\/\/doi.org\/10.1109\/mwscas.2018.8624044 2-s2.0-85062226923.","DOI":"10.1109\/MWSCAS.2018.8624044"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cjtee.2021.07.006"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/s2468-1253(21)00101-1"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.109723"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"MousaviM. MoradiM. andChaibakhshA. Ensemble-based fault detection and isolation of an industrial Gas turbine Proceedings of the 2020 IEEE International Conference on Systems Man and Cybernetics (SMC) August 2020 Toronto Canada 2351\u20132358.","DOI":"10.1109\/SMC42975.2020.9282904"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"HuangC. LiY. andTangX. Learning deep representation for imbalanced classification Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Vegas NV USA 5375\u20135384 https:\/\/doi.org\/10.1109\/cvpr.2016.580 2-s2.0-84986295253.","DOI":"10.1109\/CVPR.2016.580"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"LiuZ. MiaoZ. ZhanX. WangJ. GongB. andStellaX. Yu Large-scale long-tailed recognition in an open world Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 2537\u20132546 https:\/\/doi.org\/10.1109\/cvpr.2019.00264.","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"ZhouB. CuiQ. andChenZ.-M. Bbn: bilateral-branch network with cumulative learning for long-tailed visual recognition 2019 https:\/\/arxiv.org\/abs\/1912.02413.","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"e_1_2_9_12_2","unstructured":"KangB. XieS. RohrbachM. YanZ. AlbertG. FengJ. andKalantidisY. Decoupling representation and classifier for long-tailed recognition 2019 https:\/\/arxiv.org\/abs\/1910.09217."},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"LinT.-Yi GoyalP. GirshickR. HeK. andDoll\u00e1rP. Focal loss for dense object detection Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy https:\/\/doi.org\/10.1109\/iccv.2017.324 2-s2.0-85041916350.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"ZhangX. FangZ. WenY. LiZ. andQiaoYu Range loss for deep face recognition with long-tailed training data Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 5409\u20135418 https:\/\/doi.org\/10.1109\/iccv.2017.578 2-s2.0-85041894908.","DOI":"10.1109\/ICCV.2017.578"},{"key":"e_1_2_9_15_2","volume-title":"Unifying Distillation and Privileged Information","author":"Lopez-Paz D.","year":"2015"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"HanH. WangW.-Y. andMaoB.-H. Borderline-smote: a new over-sampling method in imbalanced data sets learning Proceedings of the International Conference on Intelligent Computing December 2005 Chongqing China 878\u2013887 https:\/\/doi.org\/10.1007\/11538059_91.","DOI":"10.1007\/11538059_91"},{"key":"e_1_2_9_19_2","first-page":"7029","article-title":"Learning to model the tail","volume":"30","author":"Wang Yu-X.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"WangY.-X.andHebertM. Learning to learn: model regression networks for easy small sample learning Proceedings of the European Conference on Computer Vision October 2016 Amsterdam The Netherlands https:\/\/doi.org\/10.1007\/978-3-319-46466-4_37 2-s2.0-84990032705.","DOI":"10.1007\/978-3-319-46466-4_37"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"Grant Van HornO. SongY. CuiY. SunC. ShepardA. AdamH. PeronaP. andBelongieS. The inaturalist species classification and detection dataset Proceedings of the IEEE conference on computer vision and pattern recognition June 2018 Salt Lake City UT USA https:\/\/doi.org\/10.1109\/cvpr.2018.00914 2-s2.0-85062853151.","DOI":"10.1109\/CVPR.2018.00914"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"GuptaA. DollarP. andGirshickR. Lvis: a dataset for large vocabulary instance seg- mentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 5356\u20135364 https:\/\/doi.org\/10.1109\/cvpr.2019.00550.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2008.239"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"ZhongY. DengW. WangM. HuJ. PengJ. TaoX. andHuangY. Unequal-training for deep face recognition with long-tailed noisy data Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 7812\u20137821 https:\/\/doi.org\/10.1109\/cvpr.2019.00800.","DOI":"10.1109\/CVPR.2019.00800"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"e_1_2_9_26_2","first-page":"1","article-title":"C4. 5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling","volume":"11","author":"Drummond C.","year":"2003","journal-title":"Workshop on learning from imbalanced datasets II"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.3233\/ida-2002-6504"},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"MahajanD. GirshickR. RamanathanV. HeK. PaluriM. LiY. BharambeA. andvan der MaatenL. Exploring the limits of weakly supervised pretraining Proceedings of the European Conference on Computer Vision (ECCV) September 2018 Munich Germany 181\u2013196 https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12 2-s2.0-85055453845.","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"ShenL. LinZ. andHuangQ. Relay backpropagation for effective learning of deep convolutional neural networks Proceedings of the European Conference on Computer Vision October 2016 Amsterdam The Netherlands https:\/\/doi.org\/10.1007\/978-3-319-46478-7_29 2-s2.0-84990068179.","DOI":"10.1007\/978-3-319-46478-7_29"},{"key":"e_1_2_9_30_2","unstructured":"RenM. ZengW. YangB. andUrtasunR. Learning to reweight examples for robust deep learning 2018 https:\/\/arxiv.org\/abs\/1803.09050."},{"key":"e_1_2_9_31_2","unstructured":"ShuJ. QiX. YiL. ZhaoQ. ZhouS. XuZ. andMengD. Meta- weight-net: learning an explicit mapping for sample weighting 2019 https:\/\/arxiv.org\/abs\/1902.07379."},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"YinXi XiangYu SohnK. LiuX. andChandrakerM. Feature trans- fer learning for face recognition with under-represented data Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 5704\u20135713 https:\/\/doi.org\/10.1109\/cvpr.2019.00585.","DOI":"10.1109\/CVPR.2019.00585"},{"key":"e_1_2_9_33_2","unstructured":"BuciluaC. CaruanaR. andNiculescu-MizilA. Model Compression. 2006."},{"key":"e_1_2_9_34_2","unstructured":"HintonG. Oriol Vinyals andDeanJ. Distilling the Knowledge in a Neural Network. 2014."},{"key":"e_1_2_9_35_2","unstructured":"RomeroA. BallasN. KahouS. E. AntoineC. GattaC. andBengioY. Fitnets: Hints for thin deep nets. 2015."},{"key":"e_1_2_9_36_2","unstructured":"ZagoruykoS.andKomodakisN. Paying more Attention to Attention: Improving the Performance Of Convolutional Neural Networks via Attention Transfer. 2017."},{"key":"e_1_2_9_37_2","unstructured":"FurlanelloT. LiptonZ. C. andTschannenM. Laurent Itti and Anima Anandku- mar. Born Again Neural Networks 2018."},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"LanXu ZhuX. andGongS. Self-Referenced Deep Learning. 2018.","DOI":"10.1007\/978-3-030-20890-5_19"},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"XiangL.andDingG. Learning from multiple experts: self-paced knowledge distillation for long-tailed classification 2020 https:\/\/arxiv.org\/abs\/2001.01536 https:\/\/doi.org\/10.1007\/978-3-030-58558-7_15.","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"e_1_2_9_40_2","unstructured":"HuangZ.andWangN. Like what you like: knowledge distill via neuron selectivity transfer 2017 https:\/\/arxiv.org\/abs\/1707.01219."},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"Oh SongH. XiangY. andJegelkaS. Deep metric learning via lifted structured feature embedding Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Vegas NV USA 4004\u20134012 https:\/\/doi.org\/10.1109\/cvpr.2016.434 2-s2.0-84986266755.","DOI":"10.1109\/CVPR.2016.434"},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"GidarisS.andKomodakisN. Dynamic few-shot visual learning without forgetting Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 4367\u20134375 https:\/\/doi.org\/10.1109\/cvpr.2018.00459 2-s2.0-85062721826.","DOI":"10.1109\/CVPR.2018.00459"},{"key":"e_1_2_9_43_2","unstructured":"RenJ. YuC. andShengS. Balanced meta-softmax for long-tailed visual recognition 2020 https:\/\/arxiv.org\/abs\/2007.10740."}],"updated-by":[{"DOI":"10.1155\/2023\/9870606","type":"retraction","label":"Retraction","source":"retraction-watch","updated":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"record-id":"47186"},{"DOI":"10.1155\/2023\/9870606","type":"retraction","label":"Retraction","source":"publisher","updated":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000}}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6702625.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6702625.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/6702625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T07:47:44Z","timestamp":1722930464000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/6702625"}},"subtitle":[],"editor":[{"given":"Syed Hassan","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/6702625"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6702625","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-08-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6702625"}}