{"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/prompt-learning-via-meta-regularization","title":"Prompt Learning via Meta-Regularization","arxiv_id":"2404.00851","date":"2024-04-01","proceeding":"CVPR 2024 1","authors":["Jinyoung Park","Juyeon Ko","Hyunwoo J. Kim"],"abstract":"Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks. However, most existing prompt learning methods suffer from task overfitting since the general knowledge of the pre-trained vision language models is forgotten while the prompts are finetuned on a small data set from a specific target task. To address this issue, we propose a Prompt Meta-Regularization (ProMetaR) to improve the generalizability of prompt learning for vision-language models. Specifically, ProMetaR meta-learns both the regularizer and the soft prompts to harness the task-specific knowledge from the downstream tasks and task-agnostic general knowledge from the vision-language models. Further, ProMetaR augments the task to generate multiple virtual tasks to alleviate the meta-overfitting. In addition, we provide the analysis to comprehend how ProMetaR improves the generalizability of prompt tuning in the perspective of the gradient alignment. Our extensive experiments demonstrate that our ProMetaR improves the generalizability of conventional prompt learning methods under base-to-base/base-to-new and domain generalization settings. The code of ProMetaR is available at https://github.com/mlvlab/ProMetaR.","url_abs":"https://arxiv.org/abs/2404.00851v1","url_pdf":"https://arxiv.org/pdf/2404.00851v1.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":"prompt-learning-via-meta-regularization","repo_url":"https://github.com/mlvlab/prometar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/prompt-engineering-on-caltech-101","task":"Prompt Engineering","dataset":"Caltech-101","model":"ProMetaR","rank_in_archive_order":9,"of":14,"metrics":{"Harmonic mean":"96.16"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-dtd","task":"Prompt Engineering","dataset":"DTD","model":"ProMetaR","rank_in_archive_order":6,"of":14,"metrics":{"Harmonic mean":"72.31"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-eurosat","task":"Prompt Engineering","dataset":"EuroSAT","model":"ProMetaR","rank_in_archive_order":6,"of":14,"metrics":{"Harmonic mean":"85.30"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-fgvc-aircraft","task":"Prompt Engineering","dataset":"FGVC-Aircraft","model":"ProMetaR","rank_in_archive_order":7,"of":14,"metrics":{"Harmonic mean":"40.25"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-food-101","task":"Prompt Engineering","dataset":"Food-101","model":"ProMetaR","rank_in_archive_order":4,"of":13,"metrics":{"Harmonic mean":"91.34"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet","task":"Prompt Engineering","dataset":"ImageNet","model":"ProMetaR","rank_in_archive_order":8,"of":15,"metrics":{"Harmonic mean":"74.09"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","task":"Prompt Engineering","dataset":"Oxford 102 Flower","model":"ProMetaR","rank_in_archive_order":5,"of":14,"metrics":{"Harmonic mean":"86.70"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-iiit-pet-dataset","task":"Prompt Engineering","dataset":"Oxford-IIIT Pet Dataset","model":"ProMetaR","rank_in_archive_order":8,"of":14,"metrics":{"Harmonic mean":"96.49"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-sun397","task":"Prompt Engineering","dataset":"SUN397","model":"ProMetaR","rank_in_archive_order":8,"of":14,"metrics":{"Harmonic mean":"80.82"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-stanford-cars-1","task":"Prompt Engineering","dataset":"Stanford Cars","model":"ProMetaR","rank_in_archive_order":5,"of":14,"metrics":{"Harmonic mean":"76.72"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-ucf101","task":"Prompt Engineering","dataset":"UCF101","model":"ProMetaR","rank_in_archive_order":5,"of":14,"metrics":{"Harmonic mean":"83.25"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.00851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00851"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/mlvlab/prometar","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mlvlab/ProMetaR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"ba26afd892405335","entry":"compute_ci95","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"parse_test_res.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/parse_test_res.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba26afd892405335"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"48ac2bd4dcbfb717","entry":"build_model","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/clip/model.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":"48ac2bd4dcbfb717"}},{"code_sha256_prefix":"f885244436207070","entry":"gradient_update","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"trainers/prometar.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/trainers/prometar.py","link_basis":"first_harvest_node","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":"f885244436207070"}},{"code_sha256_prefix":"fbf8c0143d9c48e3","entry":"load","repo":"mlvlab/ProMetaR","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/mlvlab/ProMetaR/blob/HEAD/clip/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":"fbf8c0143d9c48e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}