{"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/revisiting-the-power-of-prompt-for-visual","title":"Revisiting the Power of Prompt for Visual Tuning","arxiv_id":"2402.02382","date":"2024-02-04","proceeding":null,"authors":["Yuzhu Wang","Lechao Cheng","Chaowei Fang","Dingwen Zhang","Manni Duan","Meng Wang"],"abstract":"Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt length, and subpar performance in self-supervised pretraining, hindering successful contextual adaptation. This study commences by exploring the correlation evolvement between prompts and patch tokens during proficient training. Inspired by the observation that the prompt tokens tend to share high mutual information with patch tokens, we propose initializing prompts with downstream token prototypes. The strategic initialization, a stand-in for the previous initialization, substantially improves performance in fine-tuning. To refine further, we optimize token construction with a streamlined pipeline that maintains excellent performance with almost no increase in computational expenses compared to VPT. Exhaustive experiments show our proposed approach outperforms existing methods by a remarkable margin. For instance, it surpasses full fine-tuning in 19 out of 24 tasks, using less than 0.4% of learnable parameters on the FGVC and VTAB-1K benchmarks. Notably, our method significantly advances the adaptation for self-supervised pretraining, achieving impressive task performance gains of at least 10% to 30%. Besides, the experimental results demonstrate the proposed SPT is robust to prompt lengths and scales well with model capacity and training data size. We finally provide an insightful exploration into the amount of target data facilitating the adaptation of pre-trained models to downstream tasks. The code is available at https://github.com/WangYZ1608/Self-Prompt-Tuning.","url_abs":"https://arxiv.org/abs/2402.02382v3","url_pdf":"https://arxiv.org/pdf/2402.02382v3.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":[],"tasks":[{"task_slug":"visual-prompt-tuning","task_name":"Visual Prompt Tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-prompt-tuning-on-fgvc","task":"Visual Prompt Tuning","dataset":"FGVC","model":"SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":1,"of":10,"metrics":{"Mean Accuracy":"86.00"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-fgvc","task":"Visual Prompt Tuning","dataset":"FGVC","model":"SPT-Shallow(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":2,"of":10,"metrics":{"Mean Accuracy":"84.08"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-fgvc","task":"Visual Prompt Tuning","dataset":"FGVC","model":"SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":3,"of":10,"metrics":{"Mean Accuracy":"83.26"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-fgvc","task":"Visual Prompt Tuning","dataset":"FGVC","model":"SPT-Shallow(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":7,"of":10,"metrics":{"Mean Accuracy":"73.95"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-natural-7","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Natural<7>)","model":"SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":1,"of":10,"metrics":{"Mean Accuracy":"76.20"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-natural-7","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Natural<7>)","model":"SPT-Shallow(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":3,"of":10,"metrics":{"Mean Accuracy":"74.47"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-natural-7","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Natural<7>)","model":"SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":6,"of":10,"metrics":{"Mean Accuracy":"67.19"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-natural-7","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Natural<7>)","model":"SPT-Shallow(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":7,"of":10,"metrics":{"Mean Accuracy":"62.53"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-specialized-4","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Specialized<4>)","model":"SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":1,"of":10,"metrics":{"Mean Accuracy":"84.95"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-specialized-4","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Specialized<4>)","model":"SPT-Shallow(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":2,"of":10,"metrics":{"Mean Accuracy":"83.93"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-specialized-4","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Specialized<4>)","model":"SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":4,"of":10,"metrics":{"Mean Accuracy":"83.15"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-specialized-4","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Specialized<4>)","model":"SPT-Shallow(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":7,"of":10,"metrics":{"Mean Accuracy":"80.90"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-structured-8","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Structured<8>)","model":"SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":1,"of":10,"metrics":{"Mean Accuracy":"59.23"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-structured-8","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Structured<8>)","model":"SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":2,"of":10,"metrics":{"Mean Accuracy":"58.36"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-structured-8","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Structured<8>)","model":"SPT-Shallow(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)","rank_in_archive_order":3,"of":10,"metrics":{"Mean Accuracy":"55.16"},"uses_additional_data":false},{"leaderboard":"/sota/visual-prompt-tuning-on-vtab-1k-structured-8","task":"Visual Prompt Tuning","dataset":"VTAB-1k(Structured<8>)","model":"SPT-Shallow(ViT-B/16_MAE_pretrained_ImageNet-1K)","rank_in_archive_order":4,"of":10,"metrics":{"Mean Accuracy":"53.46"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.02382","atlas_url":"https://app.syntology.ai/?focus=2402.02382","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":"2402.02382"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.02382\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.02382"},"call":"get_concepts_for_paper(arxiv_id=\"2402.02382\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"204a0befd09ff0f99439487ed411c2d55aa2bfc2dab68d89c7127bc77551970b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}