{"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/dept-decoupled-prompt-tuning","title":"DePT: Decoupled Prompt Tuning","arxiv_id":"2309.07439","date":"2023-09-14","proceeding":"CVPR 2024 1","authors":["Ji Zhang","Shihan Wu","Lianli Gao","Heng Tao Shen","Jingkuan Song"],"abstract":"This work breaks through the Base-New Tradeoff (BNT)dilemma in prompt tuning, i.e., the better the tuned model generalizes to the base (or target) task, the worse it generalizes to new tasks, and vice versa. Specifically, through an in-depth analysis of the learned features of the base and new tasks, we observe that the BNT stems from a channel bias issue, i.e., the vast majority of feature channels are occupied by base-specific knowledge, resulting in the collapse of taskshared knowledge important to new tasks. To address this, we propose the Decoupled Prompt Tuning (DePT) framework, which decouples base-specific knowledge from feature channels into an isolated feature space during prompt tuning, so as to maximally preserve task-shared knowledge in the original feature space for achieving better zero-shot generalization on new tasks. Importantly, our DePT is orthogonal to existing prompt tuning methods, hence it can improve all of them. Extensive experiments on 11 datasets show the strong flexibility and effectiveness of DePT. Our code and pretrained models are available at https://github.com/Koorye/DePT.","url_abs":"https://arxiv.org/abs/2309.07439v2","url_pdf":"https://arxiv.org/pdf/2309.07439v2.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":"dept-decoupled-prompt-tuning","repo_url":"https://github.com/koorye/dept","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/prompt-engineering-on-caltech-101","task":"Prompt Engineering","dataset":"Caltech-101","model":"DePT","rank_in_archive_order":8,"of":14,"metrics":{"Harmonic mean":"96.28"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-dtd","task":"Prompt Engineering","dataset":"DTD","model":"DePT","rank_in_archive_order":9,"of":14,"metrics":{"Harmonic mean":"71.09"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-eurosat","task":"Prompt Engineering","dataset":"EuroSAT","model":"DePT","rank_in_archive_order":7,"of":14,"metrics":{"Harmonic mean":"84.88"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-fgvc-aircraft","task":"Prompt Engineering","dataset":"FGVC-Aircraft","model":"DePT","rank_in_archive_order":5,"of":14,"metrics":{"Harmonic mean":"40.73"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-food-101","task":"Prompt Engineering","dataset":"Food-101","model":"DePT","rank_in_archive_order":6,"of":13,"metrics":{"Harmonic mean":"91.22"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet","task":"Prompt Engineering","dataset":"ImageNet","model":"DePT","rank_in_archive_order":10,"of":15,"metrics":{"Harmonic mean":"74.02"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","task":"Prompt Engineering","dataset":"Oxford 102 Flower","model":"DePT","rank_in_archive_order":6,"of":14,"metrics":{"Harmonic mean":"86.46"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-iiit-pet-dataset","task":"Prompt Engineering","dataset":"Oxford-IIIT Pet Dataset","model":"DePT","rank_in_archive_order":10,"of":14,"metrics":{"Harmonic mean":"96.37"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-sun397","task":"Prompt Engineering","dataset":"SUN397","model":"DePT","rank_in_archive_order":6,"of":14,"metrics":{"Harmonic mean":"81.06"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-stanford-cars-1","task":"Prompt Engineering","dataset":"Stanford Cars","model":"DePT","rank_in_archive_order":4,"of":14,"metrics":{"Harmonic mean":"77.79"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-ucf101","task":"Prompt Engineering","dataset":"UCF101","model":"DePT","rank_in_archive_order":9,"of":14,"metrics":{"Harmonic mean":"82.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.07439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07439"}},"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/koorye/dept","reach":{"status":"ok","spdx":"GPL-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"koorye/dept","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/koorye/dept/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":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"c736029a62966e42","entry":"get_command","repo":"koorye/dept","repo_kind":"official","path":"templates.py","file_url":"https://github.com/koorye/dept/blob/HEAD/templates.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c736029a62966e42"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"koorye/dept","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/koorye/dept/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":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"koorye/dept","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/koorye/dept/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":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"48ac2bd4dcbfb717","entry":"build_model","repo":"koorye/dept","repo_kind":"official","path":"clip_maple/model.py","file_url":"https://github.com/koorye/dept/blob/HEAD/clip_maple/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"48ac2bd4dcbfb717"}},{"code_sha256_prefix":"c47aa9e5b049a11d","entry":"build_model","repo":"koorye/dept","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/koorye/dept/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":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c47aa9e5b049a11d"}},{"code_sha256_prefix":"4a6d53438b20cd99","entry":"get_config","repo":"koorye/dept","repo_kind":"official","path":"configs.py","file_url":"https://github.com/koorye/dept/blob/HEAD/configs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4a6d53438b20cd99"}},{"code_sha256_prefix":"fbf8c0143d9c48e3","entry":"load","repo":"koorye/dept","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/koorye/dept/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":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fbf8c0143d9c48e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}