This is the pytorch implementation of CDFNet. The util, train and test codes are heavily borrowed from RTFNet and MFNet.
The original dataset can be downloaded from the MFNet project page.
The following references are the papers and codes we referenced.
- Ha, Q., et al. MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes.in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2017. IEEE. Github
- Sun, Y., et al., Rtfnet: Rgb-thermal fusion network for semantic segmentation of urban scenes. 2019. 4(3): p. 2576-2583. Github License
- Hu, J., L. Shen, and G. Sun. Squeeze-and-excitation networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. Github
- Huang, X. and S. Belongie. Arbitrary style transfer in real-time with adaptive instance normalization. in Proceedings of the IEEE International Conference on Computer Vision. 2017. Github License
- Hou, Q., et al. Strip Pooling: Rethinking Spatial Pooling for Scene Parsing. 2020. arXiv:2003.13328. Github License
- MVIG-SJTU/AlphaPose Github License