{"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/cdformer-cross-domain-few-shot-object","title":"CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion","arxiv_id":"2505.00938","date":"2025-05-02","proceeding":null,"authors":["Boyuan Meng","Xiaohan Zhang","Peilin Li","Zhe Wu","Yiming Li","Wenkai Zhao","Beinan Yu","Hui-Liang Shen"],"abstract":"Cross-domain few-shot object detection (CD-FSOD) aims to detect novel objects across different domains with limited class instances. Feature confusion, including object-background confusion and object-object confusion, presents significant challenges in both cross-domain and few-shot settings. In this work, we introduce CDFormer, a cross-domain few-shot object detection transformer against feature confusion, to address these challenges. The method specifically tackles feature confusion through two key modules: object-background distinguishing (OBD) and object-object distinguishing (OOD). The OBD module leverages a learnable background token to differentiate between objects and background, while the OOD module enhances the distinction between objects of different classes. Experimental results demonstrate that CDFormer outperforms previous state-of-the-art approaches, achieving 12.9% mAP, 11.0% mAP, and 10.4% mAP improvements under the 1/5/10 shot settings, respectively, when fine-tuned.","url_abs":"https://arxiv.org/abs/2505.00938v1","url_pdf":"https://arxiv.org/pdf/2505.00938v1.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":"cdformer-cross-domain-few-shot-object","repo_url":"https://github.com/LONGXUANX/CDFormer_code","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-domain-few-shot","task_name":"Cross-Domain Few-Shot"},{"task_slug":"cross-domain-few-shot-object-detection","task_name":"Cross-Domain Few-Shot Object Detection"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"CDFormer(w/FT)","rank_in_archive_order":2,"of":16,"metrics":{" mAP":"68.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"CDFormer(w/o FT)","rank_in_archive_order":7,"of":16,"metrics":{" mAP":"37.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"CDFormer(w/FT)","rank_in_archive_order":2,"of":10,"metrics":{" mAP":"59.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"CDFormer(w/o FT)","rank_in_archive_order":3,"of":10,"metrics":{" mAP":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"CDFormer(w/FT)","rank_in_archive_order":2,"of":15,"metrics":{"mAP":"32.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"CDFormer(w/o FT)","rank_in_archive_order":14,"of":15,"metrics":{"mAP":"7.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"CDFormer(w/FT)","rank_in_archive_order":2,"of":10,"metrics":{"mAP":"35.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"CDFormer(w/o FT)","rank_in_archive_order":4,"of":10,"metrics":{"mAP":"25.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-neu","task":"Cross-Domain Few-Shot Object Detection","dataset":"NEU-DET","model":"CDFormer(w/FT)","rank_in_archive_order":2,"of":10,"metrics":{"mAP":"18.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-neu","task":"Cross-Domain Few-Shot Object Detection","dataset":"NEU-DET","model":"CDFormer(w/o FT)","rank_in_archive_order":8,"of":10,"metrics":{"mAP":"4.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"CDFormer(w/FT)","rank_in_archive_order":2,"of":16,"metrics":{"mAP":"26.4"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"CDFormer(w/o FT)","rank_in_archive_order":6,"of":16,"metrics":{"mAP":"16.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}