# CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion Source: [CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion]() Collection index: [llms.txt]() Data updated: 2026-01-02T09:46:14.947Z Authors: Boyuan Meng, Xiaohan Zhang, Peilin Li, Zhe Wu, Yiming Li, Wenkai Zhao, Beinan Yu, Hui-Liang Shen Published: 2025-05-02T00:46:25.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Few-shot Object Detection on CD-FSOD](): Few-shot Object Detection; CD-FSOD; ArTaxOr Score: 68.7. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()