Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation

1. Install MatConvNet

• The code is tested on matlab and MatConvNet

2. Citation

• Please consider citing our paper in your publications if the project helps your research.

@inproceedings{ding2018context,
  title={Context contrasted feature and gated multi-scale aggregation for scene segmentation},
  author={Ding, Henghui and Jiang, Xudong and Shuai, Bing and Qun Liu, Ai and Wang, Gang},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={2393--2402},
  year={2018}
}

and

@article{ding2020semantic,
  title={Semantic Segmentation with Context Encoding and Multi-Path Decoding},
  author={Ding, Henghui and Jiang, Xudong and Shuai, Bing and Liu, Ai Qun and Wang, Gang},
  journal={IEEE Transactions on Image Processing},
  year={2020},
  publisher={IEEE}
}