{"ID":2883860,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08165","arxiv_id":"2508.08165","title":"Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning","abstract":"Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Existing pre-trained model-based CIL methods often freeze the pre-trained network and adapt to incremental tasks using additional lightweight modules such as adapters. However, incorrect module selection during inference hurts performance, and task-specific modules often overlook shared general knowledge, leading to errors on distinguishing between similar classes across tasks. To address the aforementioned challenges, we propose integrating Task-Specific and Universal Adapters (TUNA) in this paper. Specifically, we train task-specific adapters to capture the most crucial features relevant to their respective tasks and introduce an entropy-based selection mechanism to choose the most suitable adapter. Furthermore, we leverage an adapter fusion strategy to construct a universal adapter, which encodes the most discriminative features shared across tasks. We combine task-specific and universal adapter predictions to harness both specialized and general knowledge during inference. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of our approach. Code is available at: https://github.com/LAMDA-CL/ICCV2025-TUNA","short_abstract":"Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Existing pre-trained model-based CIL methods often freeze the pre-trained network and adapt to incremental tasks using additional lightweight modules such as adapters. However, incorrect module selection dur...","url_abs":"https://arxiv.org/abs/2508.08165","url_pdf":"https://arxiv.org/pdf/2508.08165v1","authors":"[\"Yan Wang\",\"Da-Wei Zhou\",\"Han-Jia Ye\"]","published":"2025-08-11T16:41:04Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":611027,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2883860,"paper_url":"https://arxiv.org/abs/2508.08165","paper_title":"Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning","repo_url":"https://github.com/LAMDA-CL/ICCV2025-TUNA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}