{"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/vision-language-model-fine-tuning-via-simple","title":"Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification","arxiv_id":"2409.16718","date":"2024-09-25","proceeding":null,"authors":["Ming Li","Jike Zhong","Chenxin Li","Liuzhuozheng Li","Nie Lin","Masashi Sugiyama"],"abstract":"Recent advances in fine-tuning Vision-Language Models (VLMs) have witnessed the success of prompt tuning and adapter tuning, while the classic model fine-tuning on inherent parameters seems to be overlooked. It is believed that fine-tuning the parameters of VLMs with few-shot samples corrupts the pre-trained knowledge since fine-tuning the CLIP model even degrades performance. In this paper, we revisit this viewpoint, and propose a new perspective: fine-tuning the specific parameters instead of all will uncover the power of classic model fine-tuning on VLMs. Through our meticulous study, we propose ClipFit, a simple yet effective method to fine-tune CLIP without introducing any overhead of extra parameters. We demonstrate that by only fine-tuning the specific bias terms and normalization layers, ClipFit can improve the performance of zero-shot CLIP by 7.27\\% average harmonic mean accuracy. Lastly, to understand how fine-tuning in CLIPFit affects the pre-trained models, we conducted extensive experimental analyses w.r.t. changes in internal parameters and representations. We found that low-level text bias layers and the first layer normalization layer change much more than other layers. The code is available at \\url{https://github.com/minglllli/CLIPFit}.","url_abs":"https://arxiv.org/abs/2409.16718v2","url_pdf":"https://arxiv.org/pdf/2409.16718v2.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":"vision-language-model-fine-tuning-via-simple","repo_url":"https://github.com/minglllli/clipfit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.16718","atlas_url":"https://app.syntology.ai/?focus=2409.16718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16718"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/minglllli/clipfit","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/minglllli/CLIPFit","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":6,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"minglllli/CLIPFit","repo_kind":"official","path":"CLIPFit/clip/simple_tokenizer.py","file_url":"https://github.com/minglllli/CLIPFit/blob/HEAD/CLIPFit/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"ba26afd892405335","entry":"compute_ci95","repo":"minglllli/CLIPFit","repo_kind":"official","path":"CLIPFit/parse_test_res.py","file_url":"https://github.com/minglllli/CLIPFit/blob/HEAD/CLIPFit/parse_test_res.py","link_basis":"harvester_set","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":"ba26afd892405335"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"minglllli/CLIPFit","repo_kind":"official","path":"CLIPFit/clip/simple_tokenizer.py","file_url":"https://github.com/minglllli/CLIPFit/blob/HEAD/CLIPFit/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"minglllli/CLIPFit","repo_kind":"official","path":"CLIPFit/clip/simple_tokenizer.py","file_url":"https://github.com/minglllli/CLIPFit/blob/HEAD/CLIPFit/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"c47aa9e5b049a11d","entry":"build_model","repo":"minglllli/CLIPFit","repo_kind":"official","path":"CLIPFit/clip/model.py","file_url":"https://github.com/minglllli/CLIPFit/blob/HEAD/CLIPFit/clip/model.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":"c47aa9e5b049a11d"}},{"code_sha256_prefix":"fbf8c0143d9c48e3","entry":"load","repo":"minglllli/CLIPFit","repo_kind":"official","path":"CLIPFit/clip/clip.py","file_url":"https://github.com/minglllli/CLIPFit/blob/HEAD/CLIPFit/clip/clip.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":"fbf8c0143d9c48e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}