FSOD 数据集，全称 Few-Shot Object Detection Dataset，是一个高度多样化的数据集， 专为小样本目标检测而设计，本质上是为了评估新类别模型的泛化能力 (generality) 。 该数据集共有 1,000 个类别，其中 531 个 类别来自 ImageNet Dataset，469 个来自 Open Image Dataset 。

Citation

If you use this dataset in your research, please cite this paper. “` @inproceedings{fan2020fsod, title={Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector}, author={Fan, Qi and Zhuo, Wei and Tang, Chi-Keung and Tai, Yu-Wing}, booktitle={CVPR}, year={2020} }