konglong2021 / ip102

IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition

IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition

This work was accepted by CVPR 2019.

The IP102 datset contains more than 75,000 images belongs to 102 categories. A natural long-tailed distribution presents on it. In addition, we annotate 19,000 images with bounding boxes for object detection. The IP102 has a hierarchical taxonomy and the insect pests which mainly affect one specific agricultural product are grouped into the same upper-level category.

Data Download

You can download the IP102 v1.1 through the Drive or AliyunDrive.

The index and name of each insect pest sub-class in the classification task of the IP102 dataset can be found in classes.txt.

Additional Information

If you find the IP102 helpful, please cite it as

@inproceedings{Wu2019Insect,
  title={IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition},
  author={Xiaoping Wu and Chi Zhan and Yukun Lai and Ming-Ming Cheng and Jufeng Yang},
  booktitle={IEEE CVPR},
  pages={8787--8796},
  year={2019},
}

ATTN: This dataset is free for academic usage. For other purposes, please contact Xiaoping Wu ([email protected]).