{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/lessons-learned-from-a-unifying-empirical","title":"Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition","arxiv_id":"2409.16434","date":"2024-09-24","proceeding":"CVPR 2025 1","authors":["Zheda Mai","Ping Zhang","Cheng-Hao Tu","Hong-You Chen","Li Zhang","Wei-Lun Chao"],"abstract":"Parameter-efficient fine-tuning (PEFT) has attracted significant attention due to the growth of pre-trained model sizes and the need to fine-tune (FT) them for superior downstream performance. Despite a surge in new PEFT methods, a systematic study to understand their performance and suitable application scenarios is lacking, leaving questions like \"when to apply PEFT\" and \"which method to use\" largely unanswered, especially in visual recognition. In this paper, we conduct a unifying empirical study of representative PEFT methods with Vision Transformers. We systematically tune their hyperparameters to fairly compare their accuracy on downstream tasks. Our study offers a practical user guide and unveils several new insights. First, if tuned carefully, different PEFT methods achieve similar accuracy in the low-shot benchmark VTAB-1K. This includes simple approaches like FT the bias terms that were reported inferior. Second, despite similar accuracy, we find that PEFT methods make different mistakes and high-confidence predictions, likely due to their different inductive biases. Such an inconsistency (or complementarity) opens up the opportunity for ensemble methods, and we make preliminary attempts at this. Third, going beyond the commonly used low-shot tasks, we find that PEFT is also useful in many-shot regimes, achieving comparable or better accuracy than full FT while using significantly fewer parameters. Lastly, we investigate PEFT's ability to preserve a pre-trained model's robustness to distribution shifts (e.g., CLIP). Perhaps not surprisingly, PEFT approaches outperform full FT alone. However, with weight-space ensembles, full FT can better balance target distribution and distribution shift performance, suggesting a future research direction for robust PEFT.","url_abs":"https://arxiv.org/abs/2409.16434v5","url_pdf":"https://arxiv.org/pdf/2409.16434v5.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":"lessons-learned-from-a-unifying-empirical","repo_url":"https://github.com/osu-mlb/petl_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"lessons-learned-from-a-unifying-empirical","repo_url":"https://github.com/osu-mlb/vit_peft_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.16434","atlas_url":"https://app.syntology.ai/?focus=2409.16434","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2409.16434"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2409.16434\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2409.16434"},"call":"get_concepts_for_paper(arxiv_id=\"2409.16434\")"}],"by_repo":[{"repo":"osu-mlb/petl_vision","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1902.00751"],"harvested_for_calls":[{"arxiv_id":"1902.00751","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1902.00751"},"call":"get_harvested_code_for_paper(arxiv_id=\"1902.00751\")"}]},{"repo":"osu-mlb/vit_peft_vision","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"856f946194d1f043f115a422350e16659d20151c38c56daf6b6bdbb162844581","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}