{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:56:53Z","timestamp":1787169413882,"version":"build-2736575974"},"reference-count":60,"publisher":"Elsevier BV","issue":"8","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.ipm.2026.104963","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T11:18:44Z","timestamp":1781176724000},"page":"104963","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing decision boundaries in continual learning through a decoupled Gaussian framework"],"prefix":"10.1016","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0597-9866","authenticated-orcid":false,"given":"Zhikun","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yakun","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104963_b1","doi-asserted-by":"crossref","unstructured":"Ahn, H., Kwak, J., Lim, S., Bang, H., Kim, H., & Moon, T. (2021). Ss-il: Separated softmax for incremental learning. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 844\u2013853).","DOI":"10.1109\/ICCV48922.2021.00088"},{"key":"10.1016\/j.ipm.2026.104963_b2","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neunet.2020.12.003","article-title":"A comprehensive study of class incremental learning algorithms for visual tasks","volume":"135","author":"Belouadah","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.ipm.2026.104963_b3","series-title":"ECCV","first-page":"532","article-title":"Riemannian walk for incremental learning: Understanding forgetting and intransigence","author":"Chaudhry","year":"2018"},{"key":"10.1016\/j.ipm.2026.104963_b4","doi-asserted-by":"crossref","unstructured":"Chen, M., Gao, W., Liu, G., Peng, K., & Wang, C. (2023). Boundary unlearning: Rapid forgetting of deep networks via shifting the decision boundary. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7766\u20137775).","DOI":"10.1109\/CVPR52729.2023.00750"},{"key":"10.1016\/j.ipm.2026.104963_b5","series-title":"Prompt customization for continual learning","author":"Dai","year":"2024"},{"key":"10.1016\/j.ipm.2026.104963_b6","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.ipm.2026.104963_b7","series-title":"ECCV 2020","first-page":"86","article-title":"Podnet: Pooled outputs distillation for small-tasks incremental learning","author":"Douillard","year":"2020"},{"key":"10.1016\/j.ipm.2026.104963_b8","doi-asserted-by":"crossref","unstructured":"Douillard, A., Ram\u00e9, A., Couairon, G., & Cord, M. (2022). Dytox: Transformers for continual learning with dynamic token expansion. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9285\u20139295).","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"10.1016\/j.ipm.2026.104963_b9","article-title":"TIPS: Two-level prompt selection for more stability-plasticity balance in continual learning","author":"Feng","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.ipm.2026.104963_b10","series-title":"2025 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"Decoupling overlapped feature spaces: When continual learning meets fine-grain classification","author":"Feng","year":"2025"},{"issue":"3","key":"10.1016\/j.ipm.2026.104963_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103629","article-title":"SCREAM: Knowledge sharing and compact representation for class incremental learning","volume":"61","author":"Feng","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104963_b12","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.patrec.2024.05.011","article-title":"Adaptive knowledge transfer for class incremental learning","volume":"183","author":"Feng","year":"2024","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.ipm.2026.104963_b13","doi-asserted-by":"crossref","unstructured":"Gao, Z., Cen, J., & Chang, X. (2024). Consistent prompting for rehearsal-free continual learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 28463\u201328473).","DOI":"10.1109\/CVPR52733.2024.02689"},{"key":"10.1016\/j.ipm.2026.104963_b14","article-title":"Specific emitter identification by edge pattern detection and incremental open-world learning","author":"Gong","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104963_b15","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E., Desai, R., Zhu, T., Parajuli, S., Guo, M., et al. (2021). The many faces of robustness: A critical analysis of out-of-distribution generalization. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8340\u20138349).","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"10.1016\/j.ipm.2026.104963_b16","series-title":"OVOR: OnePrompt with virtual outlier regularization for rehearsal-free class-incremental learning","author":"Huang","year":"2024"},{"issue":"5","key":"10.1016\/j.ipm.2026.104963_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104157","article-title":"Continual and wisdom learning for federated learning: A comprehensive framework for robustness and debiasing","volume":"62","author":"Iqbal","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104963_b18","series-title":"Principal component analysis","author":"Jolliffe","year":"2002"},{"key":"10.1016\/j.ipm.2026.104963_b19","series-title":"Revisiting softmax masking: Stop gradient for enhancing stability in replay-based continual learning","author":"Kim","year":"2023"},{"issue":"13","key":"10.1016\/j.ipm.2026.104963_b20","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.ipm.2026.104963_b21","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013). 3d object representations for fine-grained categorization. In Proceedings of the IEEE international conference on computer vision workshops (pp. 554\u2013561).","DOI":"10.1109\/ICCVW.2013.77"},{"key":"10.1016\/j.ipm.2026.104963_b22","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"12","key":"10.1016\/j.ipm.2026.104963_b23","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"10.1016\/j.ipm.2026.104963_b24","doi-asserted-by":"crossref","first-page":"9422","DOI":"10.1109\/TNNLS.2024.3420895","article-title":"Fine-grained learning behavior-oriented knowledge distillation for graph neural networks","volume":"36","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"10.1016\/j.ipm.2026.104963_b25","doi-asserted-by":"crossref","first-page":"2123","DOI":"10.1109\/TCCN.2024.3520958","article-title":"A generic layer pruning method for signal modulation recognition deep learning models","volume":"11","author":"Lu","year":"2024","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"issue":"2","key":"10.1016\/j.ipm.2026.104963_b26","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1109\/TNNLS.2019.2909737","article-title":"G-softmax: improving intraclass compactness and interclass separability of features","volume":"31","author":"Luo","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"11","key":"10.1016\/j.ipm.2026.104963_b27","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"5","key":"10.1016\/j.ipm.2026.104963_b28","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":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104963_b29","series-title":"Psychology of learning and motivation","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","volume":"vol. 24","author":"McCloskey","year":"1989"},{"issue":"40","key":"10.1016\/j.ipm.2026.104963_b30","doi-asserted-by":"crossref","first-page":"24652","DOI":"10.1073\/pnas.2015509117","article-title":"Prevalence of neural collapse during the terminal phase of deep learning training","volume":"117","author":"Papyan","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"10.1016\/j.ipm.2026.104963_b31","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"The Annals of Mathematical Statistics"},{"key":"10.1016\/j.ipm.2026.104963_b32","series-title":"CVPR","first-page":"2001","article-title":"Icarl: Incremental classifier and representation learning","author":"Rebuffi","year":"2017"},{"issue":"3\u20134","key":"10.1016\/j.ipm.2026.104963_b33","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1093\/biomet\/52.3-4.591","article-title":"An analysis of variance test for normality (complete samples)","volume":"52","author":"Shapiro","year":"1965","journal-title":"Biometrika"},{"key":"10.1016\/j.ipm.2026.104963_b34","doi-asserted-by":"crossref","unstructured":"Smith, J. S., Karlinsky, L., Gutta, V., Cascante-Bonilla, P., Kim, D., Arbelle, A., Panda, R., Feris, R., & Kira, Z. (2023). Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11909\u201311919).","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"10.1016\/j.ipm.2026.104963_b35","article-title":"Inter-class and Intra-class relationships incorporated knowledge distillation for continual learning","author":"Sui","year":"2025","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.ipm.2026.104963_b36","doi-asserted-by":"crossref","unstructured":"Sun, H.-L., Zhou, D.-W., Zhao, H., Gan, L., Zhan, D.-C., & Ye, H.-J. (2025). Mos: Model surgery for pre-trained model-based class-incremental learning. vol. 39, In Proceedings of the AAAI conference on artificial intelligence (19), (pp. 20699\u201320707).","DOI":"10.1609\/aaai.v39i19.34281"},{"key":"10.1016\/j.ipm.2026.104963_b37","series-title":"2015 ieee information theory workshop (itw)","first-page":"1","article-title":"Deep learning and the information bottleneck principle","author":"Tishby","year":"2015"},{"key":"10.1016\/j.ipm.2026.104963_b38","series-title":"Three scenarios for continual learning","author":"Van de Ven","year":"2019"},{"issue":"7","key":"10.1016\/j.ipm.2026.104963_b39","doi-asserted-by":"crossref","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","article-title":"R\u00e9nyi divergence and Kullback-Leibler divergence","volume":"60","author":"Van Erven","year":"2014","journal-title":"Institute of Electrical and Electronics Engineers. Transactions on Information Theory"},{"key":"10.1016\/j.ipm.2026.104963_b40","series-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.ipm.2026.104963_b41","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ma, Z., Huang, Z., Wang, Y., Su, Z., & Hong, X. (2023). Isolation and impartial aggregation: A paradigm of incremental learning without interference. vol. 37, In Proceedings of the AAAI conference on artificial intelligence (pp. 10209\u201310217).","DOI":"10.1609\/aaai.v37i8.26216"},{"key":"10.1016\/j.ipm.2026.104963_b42","series-title":"European conference on computer vision","first-page":"631","article-title":"Dualprompt: Complementary prompting for rehearsal-free continual learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.ipm.2026.104963_b43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C.-Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., & Pfister, T. (2022). Learning to prompt for continual learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 139\u2013149).","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"10.1016\/j.ipm.2026.104963_b44","series-title":"ECCV 2022","first-page":"398","article-title":"Foster: Feature boosting and compression for class-incremental learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.ipm.2026.104963_b45","series-title":"ICLR","first-page":"685","article-title":"Improved sample complexities for deep neural networks and robust classification via an all-layer margin","author":"Wei","year":"2019"},{"key":"10.1016\/j.ipm.2026.104963_b46","series-title":"European conference on computer vision","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"Wen","year":"2016"},{"key":"10.1016\/j.ipm.2026.104963_b47","series-title":"CVPR","first-page":"374","article-title":"Large scale incremental learning","author":"Wu","year":"2019"},{"key":"10.1016\/j.ipm.2026.104963_b48","unstructured":"Xiao, C., & Hou, L. (2026). Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization. In Proceedings of the ACM web conference 2026 (pp. 6743\u20136754)."},{"key":"10.1016\/j.ipm.2026.104963_b49","unstructured":"Xu, M., Liu, H., Peng, N., Chen, Q., & Xiao, C. (2026). Affordance-First Decomposition for Continual Learning in Video-Language Understanding. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3908\u20133919)."},{"key":"10.1016\/j.ipm.2026.104963_b50","doi-asserted-by":"crossref","unstructured":"Yan, S., Xie, J., & He, X. (2021). Der: Dynamically expandable representation for class incremental learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3014\u20133023).","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"10.1016\/j.ipm.2026.104963_b51","doi-asserted-by":"crossref","unstructured":"Zhang, G., Wang, L., Kang, G., Chen, L., & Wei, Y. (2023). Slca: Slow learner with classifier alignment for continual learning on a pre-trained model. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 19148\u201319158).","DOI":"10.1109\/ICCV51070.2023.01754"},{"issue":"1","key":"10.1016\/j.ipm.2026.104963_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103899","article-title":"DST: Continual event prediction by decomposing and synergizing the task commonality and specificity","volume":"62","author":"Zhang","year":"2025","journal-title":"Information Processing & Management"},{"issue":"6","key":"10.1016\/j.ipm.2026.104963_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104224","article-title":"A soft-masking continual pre-training method based on domain knowledge relevance","volume":"62","author":"Zhao","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104963_b54","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xiao, X., Gan, G., Zhang, B., & Xia, S.-T. (2020). Maintaining discrimination and fairness in class incremental learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13208\u201313217).","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"10.1016\/j.ipm.2026.104963_b55","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhou, D.-W., Ye, H.-J., & Zhan, D.-C. (2025). Task-Agnostic Guided Feature Expansion for Class-Incremental Learning. In Proceedings of the computer vision and pattern recognition conference (pp. 10099\u201310109).","DOI":"10.1109\/CVPR52734.2025.00944"},{"key":"10.1016\/j.ipm.2026.104963_b56","unstructured":"Zheng, B., Zhou, D.-W., et al. Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning. In ICML (pp. 41\u201354)."},{"key":"10.1016\/j.ipm.2026.104963_b57","series-title":"IJCAI","first-page":"8363","article-title":"Continual learning with pre-trained models: A survey","author":"Zhou","year":"2024"},{"key":"10.1016\/j.ipm.2026.104963_b58","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3429383","article-title":"Class-incremental learning: A survey","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104963_b59","series-title":"A model or 603 exemplars: Towards memory-efficient class-incremental learning","author":"Zhou","year":"2022"},{"issue":"2","key":"10.1016\/j.ipm.2026.104963_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104428","article-title":"Influence of Gaussian distribution on performance metrics in continuous reinforcement learning","volume":"63","author":"Zhou","year":"2026","journal-title":"Information Processing & Management"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003547?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003547?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T01:49:28Z","timestamp":1785894568000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326003547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":60,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["S0306457326003547"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104963","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing decision boundaries in continual learning through a decoupled Gaussian framework","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104963","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104963"}}