This project consists of multiple experiments, each in their own subdirectories. We describe each of them briefly. Instructions on how to run them are in the respective subdirectories.
- AdaptSegNet: Unsupervised Domain Adaptation method for semantic segmentation. Adapted from Tsai et al.'s [1] work, from their GitHub repository here
- To run this,
- smoke-advent: Unsupervised Domain Adaptation for semantic segmentation using Entropy Minimization. Adapted from Vu et al.'s [2] work, from their Github repository here
- Generative Adversarial Networks for Image style transfer:
- Deep FCNs for smoke segmentation: UNet [5]
[1] Y.-H. Tsai and W.-C. Hung and S. Schulter and K. Sohn and M.-H. Yang and M. Chandraker (2018). Learning to Adapt Structured Output Space for Semantic Segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
[2] Vu, Tuan-Hung and Jain, Himalaya and Bucher, Maxime and Cord, Mathieu and P{'e}rez, Patrick (2019). ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
[3] Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros (2017). Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks IEEE International Conference on Computer Vision (ICCV)
[4] Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros (2017). Image-to-Image Translation with Conditional Adversarial Networks IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
[5] Olaf Ronneberger, Philipp Fischer, Thomas Brox (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation International Conference on Medical image computing and computer-assisted intervention