{"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/semi-supervised-domain-generalization-for-1","title":"Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment","arxiv_id":"2309.13525","date":"2023-09-24","proceeding":"BMVC 2023 11","authors":["Sina Malakouti","Adriana Kovashka"],"abstract":"Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to distinguish between objects and achieve accurate detection. In this paper, we are the first to address the problem of semi-supervised domain generalization by exploring vision-language pre-training and enforcing feature alignment through the language space. We employ a novel Cross-Domain Descriptive Multi-Scale Learning (CDDMSL) aiming to maximize the agreement between descriptions of an image presented with different domain-specific characteristics in the embedding space. CDDMSL significantly outperforms existing methods, achieving 11.7% and 7.5% improvement in DG and DA settings, respectively. Comprehensive analysis and ablation studies confirm the effectiveness of our method, positioning CDDMSL as a promising approach for domain generalization in object detection tasks.","url_abs":"https://arxiv.org/abs/2309.13525v1","url_pdf":"https://arxiv.org/pdf/2309.13525v1.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":"semi-supervised-domain-generalization-for-1","repo_url":"https://github.com/sinamalakouti/CDDMSL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semi-supervised-domain-generalization","task_name":"Semi-Supervised Domain Generalization"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-bdd100k","task":"Object Detection","dataset":"BDD100K","model":"CDDMSL","rank_in_archive_order":1,"of":1,"metrics":{"MAP":"27.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-cityscapes-to-foggy","task":"Object Detection","dataset":"Cityscapes to Foggy Cityscapes","model":"CDDMSL","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"54.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-clipart1k","task":"Object Detection","dataset":"Clipart1k","model":"CDDMSL","rank_in_archive_order":1,"of":1,"metrics":{"MAP":"39.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-comic2k","task":"Object Detection","dataset":"Comic2k","model":"CDDMSL","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-pascal-voc-to-comic2k","task":"Object Detection","dataset":"PASCAL VOC to Comic2k","model":"CDDMSL","rank_in_archive_order":2,"of":2,"metrics":{"mAP":"46.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-pascal-voc-to","task":"Object Detection","dataset":"PASCAL VOC to Watercolor2k","model":"CDDMSL","rank_in_archive_order":2,"of":2,"metrics":{"mAp":"49.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-pascal-voc-to-clipart1k","task":"Object Detection","dataset":"Pascal VOC to Clipart1K","model":"CDDMSL","rank_in_archive_order":3,"of":3,"metrics":{"mAP":"40.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-watercolor2k","task":"Object Detection","dataset":"Watercolor2k","model":"CDDMSL","rank_in_archive_order":1,"of":1,"metrics":{"MAP":"49.8"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}