{"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/facing-the-elephant-in-the-room-visual-prompt","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","arxiv_id":"2401.12902","date":"2024-01-23","proceeding":null,"authors":["Cheng Han","Qifan Wang","Yiming Cui","Wenguan Wang","Lifu Huang","Siyuan Qi","Dongfang Liu"],"abstract":"As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning (VPT) as a parameter-efficient transfer learning technique has gained attention due to its superior performance compared to traditional full-finetuning. However, the conditions favoring VPT (the ``when\") and the underlying rationale (the ``why\") remain unclear. In this paper, we conduct a comprehensive analysis across 19 distinct datasets and tasks. To understand the ``when\" aspect, we identify the scenarios where VPT proves favorable by two dimensions: task objectives and data distributions. We find that VPT is preferrable when there is 1) a substantial disparity between the original and the downstream task objectives (e.g., transitioning from classification to counting), or 2) a similarity in data distributions between the two tasks (e.g., both involve natural images). In exploring the ``why\" dimension, our results indicate VPT's success cannot be attributed solely to overfitting and optimization considerations. The unique way VPT preserves original features and adds parameters appears to be a pivotal factor. Our study provides insights into VPT's mechanisms, and offers guidance for its optimal utilization.","url_abs":"https://arxiv.org/abs/2401.12902v1","url_pdf":"https://arxiv.org/pdf/2401.12902v1.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":"facing-the-elephant-in-the-room-visual-prompt","repo_url":"https://github.com/ChengHan111/VPT-or-FT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"visual-prompt-tuning","task_name":"Visual Prompt Tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.12902","atlas_url":"https://app.syntology.ai/?focus=2401.12902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12902"}},"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/ChengHan111/VPT-or-FT","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"540bd73960d859c8","entry":"find_best_MtMtp","repo":"ChengHan111/VPT-or-FT","repo_kind":"official","path":"tune_vtab_PruningRewind_CVK_imagenet1k.py","file_url":"https://github.com/ChengHan111/VPT-or-FT/blob/HEAD/tune_vtab_PruningRewind_CVK_imagenet1k.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"540bd73960d859c8"}},{"code_sha256_prefix":"f24fe10a4c3795a2","entry":"find_best_lrwd","repo":"ChengHan111/VPT-or-FT","repo_kind":"official","path":"five_runs_fgvc.py","file_url":"https://github.com/ChengHan111/VPT-or-FT/blob/HEAD/five_runs_fgvc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f24fe10a4c3795a2"}},{"code_sha256_prefix":"0f806382f4ff9673","entry":"find_best_lrwd","repo":"ChengHan111/VPT-or-FT","repo_kind":"official","path":"tune_fgvc_fiveRuns.py","file_url":"https://github.com/ChengHan111/VPT-or-FT/blob/HEAD/tune_fgvc_fiveRuns.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0f806382f4ff9673"}},{"code_sha256_prefix":"96cd94d7836ffe52","entry":"find_best_lrwd","repo":"ChengHan111/VPT-or-FT","repo_kind":"official","path":"tune_vtab_AS.py","file_url":"https://github.com/ChengHan111/VPT-or-FT/blob/HEAD/tune_vtab_AS.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"96cd94d7836ffe52"}},{"code_sha256_prefix":"3e009472c0d2fa50","entry":"find_best_lrwd","repo":"ChengHan111/VPT-or-FT","repo_kind":"official","path":"tune_vtab_PruningRewind_CVK_imagenet1k.py","file_url":"https://github.com/ChengHan111/VPT-or-FT/blob/HEAD/tune_vtab_PruningRewind_CVK_imagenet1k.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":"3e009472c0d2fa50"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}