{"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/promptstyler-prompt-driven-style-generation","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","arxiv_id":"2307.15199","date":"2023-07-27","proceeding":"ICCV 2023 1","authors":["Junhyeong Cho","Gilhyun Nam","Sungyeon Kim","Hunmin Yang","Suha Kwak"],"abstract":"In a joint vision-language space, a text feature (e.g., from \"a photo of a dog\") could effectively represent its relevant image features (e.g., from dog photos). Also, a recent study has demonstrated the cross-modal transferability phenomenon of this joint space. From these observations, we propose PromptStyler which simulates various distribution shifts in the joint space by synthesizing diverse styles via prompts without using any images to deal with source-free domain generalization. The proposed method learns to generate a variety of style features (from \"a S* style of a\") via learnable style word vectors for pseudo-words S*. To ensure that learned styles do not distort content information, we force style-content features (from \"a S* style of a [class]\") to be located nearby their corresponding content features (from \"[class]\") in the joint vision-language space. After learning style word vectors, we train a linear classifier using synthesized style-content features. PromptStyler achieves the state of the art on PACS, VLCS, OfficeHome and DomainNet, even though it does not require any images for training.","url_abs":"https://arxiv.org/abs/2307.15199v2","url_pdf":"https://arxiv.org/pdf/2307.15199v2.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":"promptstyler-prompt-driven-style-generation","repo_url":"https://github.com/zhanghr2001/promptta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-modal-classification","task_name":"Multi-modal Classification"},{"task_slug":"multimodal-deep-learning","task_name":"Multimodal Deep Learning"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"source-free-domain-generalization","task_name":"Source-free Domain Generalization"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"arcface","method_name":"ArcFace"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"PromptStyler (CLIP, ViT-L/14)","rank_in_archive_order":2,"of":38,"metrics":{"Average Accuracy":"65.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"PromptStyler (CLIP, ViT-B/16)","rank_in_archive_order":15,"of":38,"metrics":{"Average Accuracy":"59.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"PromptStyler (CLIP, ResNet-50)","rank_in_archive_order":22,"of":38,"metrics":{"Average Accuracy":"49.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"PromptStyler (CLIP, ViT-L/14)","rank_in_archive_order":2,"of":45,"metrics":{"Average Accuracy":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"PromptStyler (CLIP, ViT-B/16)","rank_in_archive_order":10,"of":45,"metrics":{"Average Accuracy":"83.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"PromptStyler (CLIP, ResNet-50)","rank_in_archive_order":21,"of":45,"metrics":{"Average Accuracy":"73.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"PromptStyler (CLIP, ViT-L/14)","rank_in_archive_order":2,"of":133,"metrics":{"Average Accuracy":"98.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"PromptStyler (CLIP, ViT-B/16)","rank_in_archive_order":7,"of":133,"metrics":{"Average Accuracy":"97.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"PromptStyler (CLIP, ResNet-50)","rank_in_archive_order":17,"of":133,"metrics":{"Average Accuracy":"93.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"PromptStyler (CLIP, ViT-B/16)","rank_in_archive_order":7,"of":37,"metrics":{"Average Accuracy":"82.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"PromptStyler (CLIP, ViT-L/14)","rank_in_archive_order":9,"of":37,"metrics":{"Average Accuracy":"82.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"PromptStyler (CLIP, ResNet-50)","rank_in_archive_order":12,"of":37,"metrics":{"Average Accuracy":"82.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.15199","atlas_url":"https://app.syntology.ai/?focus=2307.15199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15199"}},"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/zhanghr2001/promptta","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":"0944240e80ec7625","entry":"get_clones","repo":"zhanghr2001/promptta","repo_kind":"listed","path":"utils/clip_part.py","file_url":"https://github.com/zhanghr2001/promptta/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}