{"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/visual-prompting-via-image-inpainting","title":"Visual Prompting via Image Inpainting","arxiv_id":"2209.00647","date":"2022-09-01","proceeding":null,"authors":["Amir Bar","Yossi Gandelsman","Trevor Darrell","Amir Globerson","Alexei A. Efros"],"abstract":"How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by prompting in NLP, this paper investigates visual prompting: given input-output image example(s) of a new task at test time and a new input image, the goal is to automatically produce the output image, consistent with the given examples. We show that posing this problem as simple image inpainting - literally just filling in a hole in a concatenated visual prompt image - turns out to be surprisingly effective, provided that the inpainting algorithm has been trained on the right data. We train masked auto-encoders on a new dataset that we curated - 88k unlabeled figures from academic papers sources on Arxiv. We apply visual prompting to these pretrained models and demonstrate results on various downstream image-to-image tasks, including foreground segmentation, single object detection, colorization, edge detection, etc.","url_abs":"https://arxiv.org/abs/2209.00647v1","url_pdf":"https://arxiv.org/pdf/2209.00647v1.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":"visual-prompting-via-image-inpainting","repo_url":"https://github.com/amirbar/visual_prompting","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"foreground-segmentation","task_name":"Foreground Segmentation"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"personalized-segmentation","task_name":"Personalized Segmentation"},{"task_slug":"visual-prompting","task_name":"Visual Prompting"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"pixel-prediction","method_name":"Inpainting"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"computer-vision-arxiv-figures","name":"Computer Vision Arxiv Figures","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/personalized-segmentation-on-perseg","task":"Personalized Segmentation","dataset":"PerSeg","model":"Visual Prompting","rank_in_archive_order":5,"of":6,"metrics":{"mIoU":"65.88"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.00647","atlas_url":"https://app.syntology.ai/?focus=2209.00647","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":"2209.00647"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2209.00647\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2209.00647"},"call":"get_concepts_for_paper(arxiv_id=\"2209.00647\")"}],"by_repo":[{"repo":"amirbar/visual_prompting","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"2a829db43422734cd2d96251487569164180b4ae0d432d054d5e1fa78d785dcb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}