{"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/neural-prompt-search","title":"Neural Prompt Search","arxiv_id":"2206.04673","date":"2022-06-09","proceeding":null,"authors":["Yuanhan Zhang","Kaiyang Zhou","Ziwei Liu"],"abstract":"The size of vision models has grown exponentially over the last few years, especially after the emergence of Vision Transformer. This has motivated the development of parameter-efficient tuning methods, such as learning adapter layers or visual prompt tokens, which allow a tiny portion of model parameters to be trained whereas the vast majority obtained from pre-training are frozen. However, designing a proper tuning method is non-trivial: one might need to try out a lengthy list of design choices, not to mention that each downstream dataset often requires custom designs. In this paper, we view the existing parameter-efficient tuning methods as \"prompt modules\" and propose Neural prOmpt seArcH (NOAH), a novel approach that learns, for large vision models, the optimal design of prompt modules through a neural architecture search algorithm, specifically for each downstream dataset. By conducting extensive experiments on over 20 vision datasets, we demonstrate that NOAH (i) is superior to individual prompt modules, (ii) has a good few-shot learning ability, and (iii) is domain-generalizable. The code and models are available at https://github.com/Davidzhangyuanhan/NOAH.","url_abs":"https://arxiv.org/abs/2206.04673v2","url_pdf":"https://arxiv.org/pdf/2206.04673v2.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":"neural-prompt-search","repo_url":"https://github.com/ZhangYuanhan-AI/NOAH","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-omnibenchmark","task":"Image Classification","dataset":"OmniBenchmark","model":"NOAH-ViTB/16","rank_in_archive_order":1,"of":22,"metrics":{"Average Top-1 Accuracy":"47.6"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04673"}},"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/ZhangYuanhan-AI/NOAH","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_honours":2,"ran_fixture":3,"unverified":3},"by_repo_kind":{"official":{"samples":9,"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":"4352f21759f08de9","entry":"build_transform","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"lib/datasets.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/lib/datasets.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":"4352f21759f08de9"}},{"code_sha256_prefix":"72a860a9aff50105","entry":"calc_dropout","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"model/supernet_transformer_prompt.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/supernet_transformer_prompt.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72a860a9aff50105"}},{"code_sha256_prefix":"39eace7e2822504f","entry":"drop_path","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"code_sha256_prefix":"08a5be1ffa0676e3","entry":"gelu","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"model/supernet_transformer_prompt.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/supernet_transformer_prompt.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08a5be1ffa0676e3"}},{"code_sha256_prefix":"191b2735955d18f4","entry":"resize_pos_embed","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"model/supernet_vision_transformer_timm.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/supernet_vision_transformer_timm.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"191b2735955d18f4"}},{"code_sha256_prefix":"02566da69866c48c","entry":"trunc_normal_","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02566da69866c48c"}},{"code_sha256_prefix":"3d5d962b181c73fb","entry":"build_dataset","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"lib/datasets.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/lib/datasets.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":"3d5d962b181c73fb"}},{"code_sha256_prefix":"6d8a1f8a0697180f","entry":"checkpoint_filter_fn","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"model/supernet_vision_transformer_timm.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/supernet_vision_transformer_timm.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":"6d8a1f8a0697180f"}},{"code_sha256_prefix":"3f3ae80f9a34d92b","entry":"sample_configs","repo":"ZhangYuanhan-AI/NOAH","repo_kind":"official","path":"supernet_engine_prompt.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/supernet_engine_prompt.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":"3f3ae80f9a34d92b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}