{"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/diversity-aware-meta-visual-prompting","title":"Diversity-Aware Meta Visual Prompting","arxiv_id":"2303.08138","date":"2023-03-14","proceeding":"CVPR 2023 1","authors":["Qidong Huang","Xiaoyi Dong","Dongdong Chen","Weiming Zhang","Feifei Wang","Gang Hua","Nenghai Yu"],"abstract":"We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone. A challenging issue in visual prompting is that image datasets sometimes have a large data diversity whereas a per-dataset generic prompt can hardly handle the complex distribution shift toward the original pretraining data distribution properly. To address this issue, we propose a dataset Diversity-Aware prompting strategy whose initialization is realized by a Meta-prompt. Specifically, we cluster the downstream dataset into small homogeneity subsets in a diversity-adaptive way, with each subset has its own prompt optimized separately. Such a divide-and-conquer design reduces the optimization difficulty greatly and significantly boosts the prompting performance. Furthermore, all the prompts are initialized with a meta-prompt, which is learned across several datasets. It is a bootstrapped paradigm, with the key observation that the prompting knowledge learned from previous datasets could help the prompt to converge faster and perform better on a new dataset. During inference, we dynamically select a proper prompt for each input, based on the feature distance between the input and each subset. Through extensive experiments, our DAM-VP demonstrates superior efficiency and effectiveness, clearly surpassing previous prompting methods in a series of downstream datasets for different pretraining models. Our code is available at: \\url{https://github.com/shikiw/DAM-VP}.","url_abs":"https://arxiv.org/abs/2303.08138v1","url_pdf":"https://arxiv.org/pdf/2303.08138v1.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":"diversity-aware-meta-visual-prompting","repo_url":"https://github.com/shikiw/dam-vp","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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.08138","atlas_url":"https://app.syntology.ai/?focus=2303.08138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08138"}},"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/shikiw/dam-vp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/shikiw/DAM-VP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"fe803eb0c1276891","entry":"fixed_patch","repo":"shikiw/DAM-VP","repo_kind":"official","path":"models/prompters.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/models/prompters.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":"fe803eb0c1276891"}},{"code_sha256_prefix":"0704fe8dcb551efd","entry":"get_dataset_classes","repo":"shikiw/DAM-VP","repo_kind":"official","path":"data_utils/loader.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/data_utils/loader.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":"0704fe8dcb551efd"}},{"code_sha256_prefix":"6edbfc9b90401b1e","entry":"get_transforms","repo":"shikiw/DAM-VP","repo_kind":"official","path":"data_utils/transforms.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/data_utils/transforms.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":"6edbfc9b90401b1e"}},{"code_sha256_prefix":"8dfb98b7312109ac","entry":"load_model_to_device","repo":"shikiw/DAM-VP","repo_kind":"official","path":"models/builder.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/models/builder.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":"8dfb98b7312109ac"}},{"code_sha256_prefix":"0076091e5644c4a0","entry":"padding","repo":"shikiw/DAM-VP","repo_kind":"official","path":"models/prompters.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/models/prompters.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":"0076091e5644c4a0"}},{"code_sha256_prefix":"5debe27f7868e61c","entry":"random_patch","repo":"shikiw/DAM-VP","repo_kind":"official","path":"models/prompters.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/models/prompters.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":"5debe27f7868e61c"}},{"code_sha256_prefix":"b32782e33156c848","entry":"refine_classname","repo":"shikiw/DAM-VP","repo_kind":"official","path":"meta-training/main_clip.py","file_url":"https://github.com/shikiw/DAM-VP/blob/HEAD/meta-training/main_clip.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}