The FSOD dataset, full name Few-Shot Object Detection Dataset, is a highly diverse dataset designed for small-sample target detection. Its essence is to evaluate the generalization ability of new category models. The dataset has a total of 1,000 categories, 531 of which are from the ImageNet Dataset and 469 from the 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} }