{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:15:33Z","timestamp":1783656933697,"version":"3.55.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116525","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T16:13:11Z","timestamp":1782749591000},"page":"116525","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Eliciting CLIP\u2019s intrinsic attribute knowledge through a dual-cache guided mechanism for class-incremental learning"],"prefix":"10.1016","volume":"350","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0827-640X","authenticated-orcid":false,"given":"Shengcheng","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9574-0542","authenticated-orcid":false,"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8195-4978","authenticated-orcid":false,"given":"Yaomin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4511-4813","authenticated-orcid":false,"given":"Faming","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guixu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116525_b1","doi-asserted-by":"crossref","unstructured":"S.-A. Rebuffi, A. Kolesnikov, G. Sperl, C.H. Lampert, icarl: Incremental classifier and representation learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2001\u20132010.","DOI":"10.1109\/CVPR.2017.587"},{"issue":"12","key":"10.1016\/j.knosys.2026.116525_b2","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 Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10.1016\/j.knosys.2026.116525_b3","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 Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116525_b4","doi-asserted-by":"crossref","unstructured":"F. Zhu, X.-Y. Zhang, C. Wang, F. Yin, C.-L. Liu, Prototype augmentation and self-supervision for incremental learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5871\u20135880.","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"10.1016\/j.knosys.2026.116525_b5","doi-asserted-by":"crossref","unstructured":"W. Zhang, P. Janson, R. Aljundi, M. Elhoseiny, Overcoming generic knowledge loss with selective parameter update, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 24046\u201324056.","DOI":"10.1109\/CVPR52733.2024.02270"},{"key":"10.1016\/j.knosys.2026.116525_b6","series-title":"European Conference on Computer Vision","first-page":"109","article-title":"Adapt without forgetting: Distill proximity from dual teachers in vision-language models","author":"Zheng","year":"2024"},{"key":"10.1016\/j.knosys.2026.116525_b7","article-title":"Continual learning with knowledge distillation: A survey","author":"Li","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116525_b8","series-title":"Clip model is an efficient continual learner","author":"Thengane","year":"2022"},{"key":"10.1016\/j.knosys.2026.116525_b9","doi-asserted-by":"crossref","unstructured":"R. Wang, X. Duan, G. Kang, J. Liu, S. Lin, S. Xu, J. L\u00fc, B. Zhang, Attriclip: A non-incremental learner for incremental knowledge learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3654\u20133663.","DOI":"10.1109\/CVPR52729.2023.00356"},{"key":"10.1016\/j.knosys.2026.116525_b10","article-title":"Learning without forgetting for vision-language models","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116525_b11","doi-asserted-by":"crossref","first-page":"129146","DOI":"10.52202\/079017-4102","article-title":"Clap4clip: Continual learning with probabilistic finetuning for vision-language models","volume":"37","author":"Jha","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116525_b12","series-title":"European Conference on Computer Vision","first-page":"214","article-title":"Class-incremental learning with clip: Adaptive representation adjustment and parameter fusion","author":"Huang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116525_b13","series-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","author":"Lialin","year":"2023"},{"key":"10.1016\/j.knosys.2026.116525_b14","doi-asserted-by":"crossref","unstructured":"L. Yu, H. Han, Z. Tao, H. Yao, C. Xu, Language Guided Concept Bottleneck Models for Interpretable Continual Learning, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14976\u201314986.","DOI":"10.1109\/CVPR52734.2025.01395"},{"key":"10.1016\/j.knosys.2026.116525_b15","series-title":"External knowledge injection for CLIP-based class-incremental learning","author":"Zhou","year":"2025"},{"key":"10.1016\/j.knosys.2026.116525_b16","series-title":"Desclip: Robust continual adaptation via general attribute descriptions for pretrained vision-language models","author":"He","year":"2025"},{"key":"10.1016\/j.knosys.2026.116525_b17","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3449109","article-title":"Continual learning of image classes with language guidance from a vision-language model","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116525_b18","series-title":"International Conference on Machine Learning","first-page":"11162","article-title":"Vit-net: Interpretable vision transformers with neural tree decoder","author":"Kim","year":"2022"},{"key":"10.1016\/j.knosys.2026.116525_b19","doi-asserted-by":"crossref","unstructured":"H. Chefer, S. Gur, L. Wolf, Transformer interpretability beyond attention visualization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 782\u2013791.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"10.1016\/j.knosys.2026.116525_b20","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8718","article-title":"TextRefiner: Internal visual feature as efficient refiner for vision-language models prompt tuning","volume":"Vol. 39","author":"Xie","year":"2025"},{"issue":"6266","key":"10.1016\/j.knosys.2026.116525_b21","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1126\/science.aab3050","article-title":"Human-level concept learning through probabilistic program induction","volume":"350","author":"Lake","year":"2015","journal-title":"Science"},{"key":"10.1016\/j.knosys.2026.116525_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.cognition.2023.105711","article-title":"Compositional diversity in visual concept learning","volume":"244","author":"Zhou","year":"2024","journal-title":"Cognition"},{"key":"10.1016\/j.knosys.2026.116525_b23","article-title":"Prompt-based concept learning for few-shot class-incremental learning","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116525_b24","article-title":"REAL: Representation enhanced analytic learning for exemplar-free class-incremental learning","author":"He","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116525_b25","article-title":"Multi-modality integrated class incremental learning networks for 3D object recognition","author":"Zhang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116525_b26","doi-asserted-by":"crossref","first-page":"50570","DOI":"10.52202\/075280-2200","article-title":"Sparse parameterization for epitomic dataset distillation","volume":"36","author":"Wei","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116525_b27","doi-asserted-by":"crossref","first-page":"10842","DOI":"10.1109\/TMM.2024.3414277","article-title":"Modeling inner-and cross-task contrastive relations for continual image classification","volume":"26","author":"Luo","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116525_b28","series-title":"Gradient projection memory for continual learning","author":"Saha","year":"2021"},{"key":"10.1016\/j.knosys.2026.116525_b29","series-title":"European Conference on Computer Vision","first-page":"219","article-title":"Select and distill: Selective dual-teacher knowledge transfer for continual learning on vision-language models","author":"Yu","year":"2024"},{"issue":"8","key":"10.1016\/j.knosys.2026.116525_b30","doi-asserted-by":"crossref","first-page":"7328","DOI":"10.1109\/TCSVT.2024.3376197","article-title":"ESDB: Expand the shrinking decision boundary via one-to-many information matching for continual learning with small memory","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116525_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130286","article-title":"Enhance the old representations\u2019 adaptability dynamically for exemplar-free continual learning","volume":"639","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.116525_b32","article-title":"CKDF-V2: effectively alleviating representation shift for continual learning with small memory","author":"Li","year":"2025","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116525_b33","doi-asserted-by":"crossref","unstructured":"S. Yan, J. Xie, X. He, Der: Dynamically expandable representation for class incremental learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3014\u20133023.","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"10.1016\/j.knosys.2026.116525_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113795","article-title":"Mote: Mixture of task-specific experts for pre-trained model-based class-incremental learning","volume":"324","author":"Li","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116525_b35","doi-asserted-by":"crossref","unstructured":"F. Ye, A.G. Bors, Task-free continual generation and representation learning via dynamic expansionable memory cluster, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 16451\u201316459.","DOI":"10.1609\/aaai.v38i15.29582"},{"key":"10.1016\/j.knosys.2026.116525_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113688","article-title":"Online task-free continual learning via discrepancy mechanism","volume":"322","author":"Ye","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116525_b37","doi-asserted-by":"crossref","unstructured":"Z. Wang, Z. Zhang, C.-Y. Lee, H. Zhang, R. Sun, X. Ren, G. Su, V. Perot, J. Dy, T. Pfister, Learning to prompt for continual learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 139\u2013149.","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"10.1016\/j.knosys.2026.116525_b38","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.knosys.2026.116525_b39","doi-asserted-by":"crossref","unstructured":"J.S. Smith, L. Karlinsky, V. Gutta, P. Cascante-Bonilla, D. Kim, A. Arbelle, R. Panda, R. Feris, Z. Kira, 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, 2023, pp. 11909\u201311919.","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"10.1016\/j.knosys.2026.116525_b40","article-title":"Visual class incremental learning with textual priors guidance based on an adapted vision-language model","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116525_b41","series-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"2866","article-title":"Texcil: Text-guided continual learning of disease with vision-language model","author":"Zhang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116525_b42","doi-asserted-by":"crossref","first-page":"5911","DOI":"10.1109\/TMM.2023.3340551","article-title":"Cross-modal alternating learning with task-aware representations for continual learning","volume":"26","author":"Li","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116525_b43","doi-asserted-by":"crossref","unstructured":"J. Rajasegaran, S. Khan, M. Hayat, F.S. Khan, M. Shah, itaml: An incremental task-agnostic meta-learning approach, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13588\u201313597.","DOI":"10.1109\/CVPR42600.2020.01360"},{"key":"10.1016\/j.knosys.2026.116525_b44","doi-asserted-by":"crossref","unstructured":"J. Xiang, E. Shlizerman, Tkil: Tangent kernel optimization for class balanced incremental learning, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 3529\u20133539.","DOI":"10.1109\/ICCVW60793.2023.00379"},{"key":"10.1016\/j.knosys.2026.116525_b45","doi-asserted-by":"crossref","unstructured":"T. Fukuda, H. Kera, K. Kawamoto, Adapter merging with centroid prototype mapping for scalable class-incremental learning, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 4884\u20134893.","DOI":"10.1109\/CVPR52734.2025.00460"},{"key":"10.1016\/j.knosys.2026.116525_b46","series-title":"Adaptive weighted parameter fusion with CLIP for class-incremental learning","author":"Guo","year":"2025"},{"key":"10.1016\/j.knosys.2026.116525_b47","series-title":"Feature calibration enhanced parameter synthesis for CLIP-based class-incremental learning","author":"Guo","year":"2025"},{"issue":"9","key":"10.1016\/j.knosys.2026.116525_b48","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116525_b49","doi-asserted-by":"crossref","unstructured":"G. Zhang, L. Wang, G. Kang, L. Chen, Y. Wei, 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, 2023, pp. 19148\u201319158.","DOI":"10.1109\/ICCV51070.2023.01754"},{"key":"10.1016\/j.knosys.2026.116525_b50","series-title":"What do vision transformers learn? a visual exploration","author":"Ghiasi","year":"2022"},{"key":"10.1016\/j.knosys.2026.116525_b51","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"10.1016\/j.knosys.2026.116525_b52","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"10.1016\/j.knosys.2026.116525_b53","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.knosys.2026.116525_b54","series-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.knosys.2026.116525_b55","series-title":"2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing","first-page":"722","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.knosys.2026.116525_b56","series-title":"European Conference on Computer Vision","first-page":"446","article-title":"Food-101\u2013mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.knosys.2026.116525_b57","doi-asserted-by":"crossref","unstructured":"Z. Li, L. Zhao, Z. Zhang, H. Zhang, D. Liu, T. Liu, D.N. Metaxas, Steering prototypes with prompt-tuning for rehearsal-free continual learning, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 2523\u20132533.","DOI":"10.1109\/WACV57701.2024.00251"},{"key":"10.1016\/j.knosys.2026.116525_b58","doi-asserted-by":"crossref","unstructured":"Q. Gao, C. Zhao, Y. Sun, T. Xi, G. Zhang, B. Ghanem, J. Zhang, A unified continual learning framework with general parameter-efficient tuning, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 11483\u201311493.","DOI":"10.1109\/ICCV51070.2023.01055"},{"key":"10.1016\/j.knosys.2026.116525_b59","doi-asserted-by":"crossref","unstructured":"D.-W. Zhou, H.-L. Sun, H.-J. Ye, D.-C. Zhan, Expandable subspace ensemble for pre-trained model-based class-incremental learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 23554\u201323564.","DOI":"10.1109\/CVPR52733.2024.02223"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012517?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012517?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T03:37:40Z","timestamp":1783654660000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126012517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":59,"alternative-id":["S0950705126012517"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116525","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Eliciting CLIP\u2019s intrinsic attribute knowledge through a dual-cache guided mechanism for class-incremental learning","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116525","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116525"}}