</> Code with Papers by Syntology

Papers › CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion

CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion

2 May 2025arXiv:2505.00938archive 2025-07-28

Boyuan Meng, Xiaohan Zhang, Peilin Li, Zhe Wu, Yiming Li, Wenkai Zhao, Beinan Yu, Hui-Liang Shen

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.

PaperPDFCode

Code

LONGXUANX/CDFormer_code officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Domain Few-ShotCross-Domain Few-Shot Object DetectionFew-Shot Object DetectionObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor CDFormer(w/FT) mAP 68.7 #2 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Artaxor CDFormer(w/o FT) mAP 37.3 #7 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Clipark1k CDFormer(w/FT) mAP 59.0 #2 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Clipark1k CDFormer(w/o FT) mAP 53.5 #3 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR CDFormer(w/FT) mAP 32.5 #2 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR CDFormer(w/o FT) mAP 7.9 #14 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DeepFish CDFormer(w/FT) mAP 35.5 #2 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DeepFish CDFormer(w/o FT) mAP 25.7 #4 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection NEU-DET CDFormer(w/FT) mAP 18.1 #2 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection NEU-DET CDFormer(w/o FT) mAP 4.0 #8 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD CDFormer(w/FT) mAP 26.4 #2 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD CDFormer(w/o FT) mAP 16.7 #6 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections