{"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/unleashing-the-power-of-visual-prompting-at","title":"Unleashing the Power of Visual Prompting At the Pixel Level","arxiv_id":"2212.10556","date":"2022-12-20","proceeding":null,"authors":["Junyang Wu","Xianhang Li","Chen Wei","Huiyu Wang","Alan Yuille","Yuyin Zhou","Cihang Xie"],"abstract":"This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image, we treat the prompt as an extra and independent learnable component. We show that the strategy of reconciling the prompt and the image matters, and find that warping the prompt around a properly shrinked image empirically works the best. Second, we re-introduce two \"old tricks\" commonly used in building transferable adversarial examples, i.e., input diversity and gradient normalization, into visual prompting. These techniques improve optimization and enable the prompt to generalize better. We provide extensive experimental results to demonstrate the effectiveness of our method. Using a CLIP model, our prompting method sets a new record of 82.8% average accuracy across 12 popular classification datasets, substantially surpassing the prior art by +5.6%. It is worth noting that this prompting performance already outperforms linear probing by +2.1% and can even match fully fine-tuning in certain datasets. In addition, our prompting method shows competitive performance across different data scales and against distribution shifts. The code is publicly available at https://github.com/UCSC-VLAA/EVP.","url_abs":"https://arxiv.org/abs/2212.10556v2","url_pdf":"https://arxiv.org/pdf/2212.10556v2.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":"unleashing-the-power-of-visual-prompting-at","repo_url":"https://github.com/ucsc-vlaa/evp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"visual-prompting","task_name":"Visual Prompting"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.10556","atlas_url":"https://app.syntology.ai/?focus=2212.10556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10556"}},"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/ucsc-vlaa/evp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"2b0c6c7780d77be3","entry":"add_weight_decay","repo":"ucsc-vlaa/evp","repo_kind":"official","path":"util/tool.py","file_url":"https://github.com/ucsc-vlaa/evp/blob/HEAD/util/tool.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b0c6c7780d77be3"}},{"code_sha256_prefix":"228b4da98f348fbe","entry":"topk","repo":"ucsc-vlaa/evp","repo_kind":"official","path":"util/tool.py","file_url":"https://github.com/ucsc-vlaa/evp/blob/HEAD/util/tool.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"228b4da98f348fbe"}},{"code_sha256_prefix":"c047c720207b8201","entry":"get_index","repo":"ucsc-vlaa/evp","repo_kind":"official","path":"util/get_index.py","file_url":"https://github.com/ucsc-vlaa/evp/blob/HEAD/util/get_index.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c047c720207b8201"}},{"code_sha256_prefix":"b32782e33156c848","entry":"refine_classname","repo":"ucsc-vlaa/evp","repo_kind":"official","path":"util/tool.py","file_url":"https://github.com/ucsc-vlaa/evp/blob/HEAD/util/tool.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b32782e33156c848"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}