SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments
Abstract
We present a novel approach for unsupervised road segmentation in adverse weather conditions such as rain or fog. This includes a new algorithm for source-free domain adaptation (SFDA) using self-supervised learning. More-over, our approach uses several techniques to address various challenges in SFDA and improve performance, including online generation of pseudo-labels and self-attention as well as use of curriculum learning, entropy minimization and model distillation. We have evaluated the performance on 6 datasets corresponding to real and synthetic adverse weather conditions. Our method outperforms all prior works on unsupervised road segmentation and SFDA by at least 10.26%, and improves the training time by 18−180×. Moreover, our self-supervised algorithm exhibits similar accuracy performance in terms of mIOU score as compared to prior supervised methods.
Cite
Text
Kothandaraman et al. "SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00339Markdown
[Kothandaraman et al. "SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/kothandaraman2021iccvw-sssfda/) doi:10.1109/ICCVW54120.2021.00339BibTeX
@inproceedings{kothandaraman2021iccvw-sssfda,
title = {{SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments}},
author = {Kothandaraman, Divya and Chandra, Rohan and Manocha, Dinesh},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2021},
pages = {3042-3052},
doi = {10.1109/ICCVW54120.2021.00339},
url = {https://mlanthology.org/iccvw/2021/kothandaraman2021iccvw-sssfda/}
}