CDFSOD-benchmark 是一个专注于跨域小样本物体检测（Cross-Domain Few-Shot Object Detection，简称 CD-FSOD）的研究项目，由北京航天航空大学和讯飞的研究团队于 2024 年发布，相关论文成果为「Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector」，已被 ECCV24 接受。该项目旨在解决在源域与目标域存在显著领域差异时的小样本物体检测问题。它包括一个用于算法评测的数据集，以及用于衡量领域差异的风格 (style) 、类间方差 (Inter-class Variance, ICV) 、无法定义的边界 (Indefinable Boundaries, IB) 等数据集指标。

Citation

@inproceedings{fu2025cross, title={Cross-domain few-shot object detection via enhanced open-set object detector}, author={Fu, Yuqian and Wang, Yu and Pan, Yixuan and Huai, Lian and Qiu, Xingyu and Shangguan, Zeyu and Liu, Tong and Fu, Yanwei and Van Gool, Luc and Jiang, Xingqun}, booktitle={European Conference on Computer Vision}, pages={247–264}, year={2025}, organization={Springer} } @inproceedings{fu2025ntire, title={NTIRE 2025 challenge on cross-domain few-shot object detection: Methods and results}, author={Fu, Yuqian and Qiu, Xingyu and Ren, Bin and Fu, Yanwei and Timofte, Radu and Sebe, Nicu and Yang, Ming-Hsuan and Van Gool, Luc and Zhang, Kaijin and Nong, Qingpeng and others}, booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference}, pages={1048–1069}, year={2025} }