{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/boosting-continual-learning-of-vision","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","arxiv_id":"2403.11549","date":"2024-03-18","proceeding":"CVPR 2024 1","authors":["Jiazuo Yu","Yunzhi Zhuge","Lu Zhang","Ping Hu","Dong Wang","Huchuan Lu","You He"],"abstract":"Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial due to (i) parameter shifts throughout lifelong learning and (ii) significant computational burdens associated with full-model tuning. In this work, we present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters in response to new tasks. To preserve the zero-shot recognition capability of vision-language models, we further introduce a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP, respectively. Through extensive experiments across various settings, our proposed method consistently outperforms previous state-of-the-art approaches while concurrently reducing parameter training burdens by 60%. Our code locates at https://github.com/JiazuoYu/MoE-Adapters4CL","url_abs":"https://arxiv.org/abs/2403.11549v2","url_pdf":"https://arxiv.org/pdf/2403.11549v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"boosting-continual-learning-of-vision","repo_url":"https://github.com/jiazuoyu/moe-adapters4cl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"boosting-continual-learning-of-vision","repo_url":"https://github.com/aimagelab/mammoth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.11549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11549"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aimagelab/mammoth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiazuoyu/moe-adapters4cl","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/JiazuoYu/MoE-Adapters4CL","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"97237f25b2120465","entry":"Adapter","repo":"JiazuoYu/MoE-Adapters4CL","repo_kind":"official","path":"cil/clip/adapter.py","file_url":"https://github.com/JiazuoYu/MoE-Adapters4CL/blob/HEAD/cil/clip/adapter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97237f25b2120465"}},{"code_sha256_prefix":"9fbea808db47dc66","entry":"project_logits","repo":"jiazuoyu/moe-adapters4cl","repo_kind":"official","path":"cil/datasets_ref/imagenet.py","file_url":"https://github.com/jiazuoyu/moe-adapters4cl/blob/HEAD/cil/datasets_ref/imagenet.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fbea808db47dc66"}},{"code_sha256_prefix":"4db506dabde16a1f","entry":"build_model","repo":"jiazuoyu/moe-adapters4cl","repo_kind":"official","path":"cil/clip/model.py","file_url":"https://github.com/jiazuoyu/moe-adapters4cl/blob/HEAD/cil/clip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4db506dabde16a1f"}},{"code_sha256_prefix":"3903d266387afea6","entry":"get_classnames","repo":"jiazuoyu/moe-adapters4cl","repo_kind":"official","path":"cil/datasets_ref/imagenet_classnames.py","file_url":"https://github.com/jiazuoyu/moe-adapters4cl/blob/HEAD/cil/datasets_ref/imagenet_classnames.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3903d266387afea6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}