{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T16:13:20Z","timestamp":1788452000131,"version":"build-2803163510"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2018-06484"],"award-info":[{"award-number":["RGPIN-2018-06484"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021202","name":"Alliance de recherche num\u00e9rique du Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021202","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12301478"],"award-info":[{"award-number":["12301478"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.neunet.2025.108017","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T01:31:33Z","timestamp":1755739893000},"page":"108017","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Rethinking softmax in incremental learning"],"prefix":"10.1016","volume":"193","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7983-8134","authenticated-orcid":false,"given":"Zheng","family":"Zhai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiali","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keshun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1257-0081","authenticated-orcid":false,"given":"Xiaoyan","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4182-6533","authenticated-orcid":false,"given":"Qiang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108017_bib0001","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"139","article-title":"Memory aware synapses: Learning what (not) to forget","author":"Aljundi","year":"2018"},{"key":"10.1016\/j.neunet.2025.108017_bib0002","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"583","article-title":"Il2m: Class incremental learning with dual memory","author":"Belouadah","year":"2019"},{"key":"10.1016\/j.neunet.2025.108017_bib0003","series-title":"Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining","first-page":"535","article-title":"Model compression","author":"Bucilu","year":"2006"},{"key":"10.1016\/j.neunet.2025.108017_bib0004","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"233","article-title":"End-to-end incremental learning","author":"Castro","year":"2018"},{"key":"10.1016\/j.neunet.2025.108017_bib0005","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"532","article-title":"Riemannian walk for incremental learning: understanding forgetting and intransigence","author":"Chaudhry","year":"2018"},{"key":"10.1016\/j.neunet.2025.108017_bib0006","unstructured":"Chrabaszcz, P., Loshchilov, I., & Hutter, F. (2017). A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv: 1707.08819."},{"key":"10.1016\/j.neunet.2025.108017_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5138","article-title":"Learning without memorizing","author":"Dhar","year":"2019"},{"key":"10.1016\/j.neunet.2025.108017_bib0008","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2025.108017_bib0009","series-title":"Computer vision-ECCV 2016: 14th European conference, Amsterdam","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"He","year":"2016"},{"issue":"9","key":"10.1016\/j.neunet.2025.108017_bib0010","article-title":"Distilling the knowledge in a neural network","volume":"1050","author":"Hinton","year":"2015","journal-title":"Stat"},{"key":"10.1016\/j.neunet.2025.108017_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"831","article-title":"Learning a unified classifier incrementally via rebalancing","author":"Hou","year":"2019"},{"key":"10.1016\/j.neunet.2025.108017_bib0012","doi-asserted-by":"crossref","first-page":"908","DOI":"10.1609\/aaai.v37i1.25170","article-title":"Resolving task confusion in dynamic expansion architectures for class incremental learning","volume":"37","author":"Huang","year":"2023","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.108017_bib0013","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","article-title":"Continual lifelong learning with neural networks: A review","volume":"113","author":"I Parisi","year":"2019","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108017_bib0014","series-title":"Understanding Gaussian attention bias of vision transformers using effective receptive fields","author":"Kim","year":"2023"},{"key":"10.1016\/j.neunet.2025.108017_bib0015","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Agnieszka grabska-barwinska, et al. overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"In Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2025.108017_bib0016","series-title":"Technical Report","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"10.1016\/j.neunet.2025.108017_bib0017","first-page":"3366","article-title":"A continual learning survey: Defying forgetting in classification tasks","volume":"44","author":"Lange","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"10.1016\/j.neunet.2025.108017_bib0018","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2025.108017_bib0019","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1007\/s11704-016-6903-6","article-title":"Lifelong machine learning: A paradigm for continuous learning","volume":"11","author":"Liu","year":"2017","journal-title":"Frontiers of Computer Science"},{"issue":"12","key":"10.1016\/j.neunet.2025.108017_bib0020","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1038\/s42256-022-00568-3","article-title":"Three types of incremental learning","volume":"4","author":"M Van de Ven","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108017_bib0021","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.neucom.2021.10.021","article-title":"Online continual learning in image classification: An empirical survey","volume":"469","author":"Mai","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.108017_bib0022","series-title":"International conference on machine learning","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"Martins","year":"2016"},{"issue":"5","key":"10.1016\/j.neunet.2025.108017_bib0023","doi-asserted-by":"crossref","first-page":"5513","DOI":"10.1109\/TPAMI.2022.3213473","article-title":"Class-incremental learning: Survey and performance evaluation on image classification","volume":"45","author":"Masana","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108017_bib0024","series-title":"Nips workshop on deep learning and unsupervised feature learning","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"},{"key":"10.1016\/j.neunet.2025.108017_bib0025","series-title":"NIPS-W","article-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2017"},{"key":"10.1016\/j.neunet.2025.108017_bib0026","series-title":"Computer vision-ECCV 2020: 16th European conference","first-page":"524","article-title":"Gdumb: A simple approach that questions our progress in continual learning","author":"Prabhu","year":"2020"},{"key":"10.1016\/j.neunet.2025.108017_bib0027","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","article-title":"ICARL: Incremental classifier and representation learning","author":"Rebuffi","year":"2001"},{"key":"10.1016\/j.neunet.2025.108017_bib0028","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.108017_bib0029","article-title":"Continual learning with deep generative replay","volume":"30","author":"Shin","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108017_bib0030","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"4292","article-title":"Incremental learning via robust parameter posterior fusion","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2025.108017_bib0031","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"374","article-title":"Large scale incremental learning","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2025.108017_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3014","article-title":"Der: Dynamically expandable representation for class incremental learning","author":"Yan","year":"2021"},{"key":"10.1016\/j.neunet.2025.108017_bib0033","series-title":"International conference on learning representations","article-title":"Lifelong learning with dynamically expandable networks","author":"Yoon","year":"2018"},{"key":"10.1016\/j.neunet.2025.108017_bib0034","series-title":"International conference on machine learning","first-page":"3987","article-title":"Continual learning through synaptic intelligence","author":"Zenke","year":"2017"},{"key":"10.1016\/j.neunet.2025.108017_bib0035","series-title":"Class-incremental learning: A survey","author":"Zhou","year":"2024"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025008974?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025008974?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T03:33:42Z","timestamp":1772854422000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025008974"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":35,"alternative-id":["S0893608025008974"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108017","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Rethinking softmax in incremental learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108017","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108017"}}