{"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/mind-the-interference-retaining-pre-trained","title":"Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models","arxiv_id":"2407.05342","date":"2024-07-07","proceeding":null,"authors":["Longxiang Tang","Zhuotao Tian","Kai Li","Chunming He","Hantao Zhou","Hengshuang Zhao","Xiu Li","Jiaya Jia"],"abstract":"This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes vary across tasks. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. However, this incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy computation overhead. To address this problem efficiently, we propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of VLMs from a perspective of avoiding information interference. Specifically, we design a fully residual mechanism to infuse newly learned knowledge into a frozen backbone, while introducing minimal adverse impacts on pre-trained knowledge. Besides, this residual property enables our distribution-aware integration calibration scheme, explicitly controlling the information implantation process for test data from unseen distributions. Experiments demonstrate that our DIKI surpasses the current state-of-the-art approach using only 0.86% of the trained parameters and requiring substantially less training time. Code is available at: https://github.com/lloongx/DIKI .","url_abs":"https://arxiv.org/abs/2407.05342v1","url_pdf":"https://arxiv.org/pdf/2407.05342v1.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":"mind-the-interference-retaining-pre-trained","repo_url":"https://github.com/lloongx/diki","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.05342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05342"}},"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/lloongx/diki","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"7d748eb753eeb8d5","entry":"cosine_loss_3d","repo":"lloongx/diki","repo_kind":"official","path":"DIKI/utils.py","file_url":"https://github.com/lloongx/diki/blob/HEAD/DIKI/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d748eb753eeb8d5"}},{"code_sha256_prefix":"ee433789c998279d","entry":"cosine_schedule_warmup","repo":"lloongx/diki","repo_kind":"official","path":"DIKI/utils.py","file_url":"https://github.com/lloongx/diki/blob/HEAD/DIKI/utils.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":"ee433789c998279d"}},{"code_sha256_prefix":"567f019e19baed3c","entry":"parse_sample","repo":"lloongx/diki","repo_kind":"official","path":"DIKI/datasets.py","file_url":"https://github.com/lloongx/diki/blob/HEAD/DIKI/datasets.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":"567f019e19baed3c"}},{"code_sha256_prefix":"3fd5b3a0c63d826c","entry":"get_dataset","repo":"lloongx/diki","repo_kind":"official","path":"DIKI/datasets.py","file_url":"https://github.com/lloongx/diki/blob/HEAD/DIKI/datasets.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":"3fd5b3a0c63d826c"}},{"code_sha256_prefix":"cde1c7bf8243185b","entry":"setup_cfg","repo":"lloongx/diki","repo_kind":"official","path":"DIKI/setup_cfg.py","file_url":"https://github.com/lloongx/diki/blob/HEAD/DIKI/setup_cfg.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":"cde1c7bf8243185b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}