{"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-based-distribution-alignment-for","title":"Prompt-based Distribution Alignment for Unsupervised Domain Adaptation","arxiv_id":"2312.09553","date":"2023-12-15","proceeding":null,"authors":["Shuanghao Bai","Min Zhang","Wanqi Zhou","Siteng Huang","Zhirong Luan","Donglin Wang","Badong Chen"],"abstract":"Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.","url_abs":"https://arxiv.org/abs/2312.09553v2","url_pdf":"https://arxiv.org/pdf/2312.09553v2.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-based-distribution-alignment-for","repo_url":"https://github.com/baishuanghao/prompt-based-distribution-alignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-office-31","task":"Unsupervised Domain Adaptation","dataset":"Office-31","model":"PDA (CLIP, ViT-B/16)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"91.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-office-home","task":"Unsupervised Domain Adaptation","dataset":"Office-Home","model":"PDA  (CLIP, ViT-B/16)","rank_in_archive_order":6,"of":20,"metrics":{"Accuracy":"85.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-office-home","task":"Unsupervised Domain Adaptation","dataset":"Office-Home","model":"PDA (CLIP, ResNet-50)","rank_in_archive_order":14,"of":20,"metrics":{"Accuracy":"75.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-visda2017","task":"Unsupervised Domain Adaptation","dataset":"VisDA2017","model":"PDA (CLIP, ViT-B/16)","rank_in_archive_order":5,"of":13,"metrics":{"Accuracy":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-visda2017","task":"Unsupervised Domain Adaptation","dataset":"VisDA2017","model":"PDA (CLIP, ResNet-101)","rank_in_archive_order":10,"of":13,"metrics":{"Accuracy":"86.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.09553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09553"}},"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/baishuanghao/prompt-based-distribution-alignment","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"fb8b765f896ca77c","entry":"fixed_patch","repo":"baishuanghao/prompt-based-distribution-alignment","repo_kind":"official","path":"utils/visual_prompt.py","file_url":"https://github.com/baishuanghao/prompt-based-distribution-alignment/blob/HEAD/utils/visual_prompt.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":"fb8b765f896ca77c"}},{"code_sha256_prefix":"98c70398b832504f","entry":"padding","repo":"baishuanghao/prompt-based-distribution-alignment","repo_kind":"official","path":"utils/visual_prompt.py","file_url":"https://github.com/baishuanghao/prompt-based-distribution-alignment/blob/HEAD/utils/visual_prompt.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":"98c70398b832504f"}},{"code_sha256_prefix":"3f8752aa7aac40b9","entry":"random_patch","repo":"baishuanghao/prompt-based-distribution-alignment","repo_kind":"official","path":"utils/visual_prompt.py","file_url":"https://github.com/baishuanghao/prompt-based-distribution-alignment/blob/HEAD/utils/visual_prompt.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":"3f8752aa7aac40b9"}},{"code_sha256_prefix":"0944240e80ec7625","entry":"get_clones","repo":"baishuanghao/prompt-based-distribution-alignment","repo_kind":"official","path":"utils/clip_part.py","file_url":"https://github.com/baishuanghao/prompt-based-distribution-alignment/blob/HEAD/utils/clip_part.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":"0944240e80ec7625"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}