Context Prior for Scene Segmentation (CVPR2020)

Implementation for "Context Prior for Scene Segmentation"

News

• We achieve 46.3% mean IoU on ADE20K val set, 53.9% mIoU on PASCAL-Context, and 81.3% mIoU on Cityscapes.

Citation

Please consider citing the ContextPrior in your publications if it helps your research.

@inproceedings{Yu-CVPR-ContextPrior-2020,
  title={Context Prior for Scene Segmentation},
  author={Yu, Changqian and Wang, Jingbo and Gao, Changxin and Yu, Gang and Shen, Chunhua and Sang, Nong},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
}