Saved in:
Bibliographic Details
Main Authors: Meng, Boyuan, Zhang, Xiaohan, Li, Peilin, Wu, Zhe, Li, Yiming, Zhao, Wenkai, Yu, Beinan, Shen, Hui-Liang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.00938
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912357593120768
author Meng, Boyuan
Zhang, Xiaohan
Li, Peilin
Wu, Zhe
Li, Yiming
Zhao, Wenkai
Yu, Beinan
Shen, Hui-Liang
author_facet Meng, Boyuan
Zhang, Xiaohan
Li, Peilin
Wu, Zhe
Li, Yiming
Zhao, Wenkai
Yu, Beinan
Shen, Hui-Liang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00938
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
Meng, Boyuan
Zhang, Xiaohan
Li, Peilin
Wu, Zhe
Li, Yiming
Zhao, Wenkai
Yu, Beinan
Shen, Hui-Liang
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.00938