Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions
Abstract
Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops in accuracy and offline adaptation may not be enough to contrast it. In this paper, we tackle Online Domain Adaptation (OnDA) for semantic segmentation. We design a pipeline that is robust to continuous domain shifts, either gradual or sudden, and we evaluate it in the case of rainy and foggy scenarios. Our experiments show that our framework can effectively adapt to new domains during deployment, while not being affected by catastrophic forgetting of the previous domains.
Cite
Text
Panagiotakopoulos et al. "Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19830-4Markdown
[Panagiotakopoulos et al. "Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/panagiotakopoulos2022eccv-online/) doi:10.1007/978-3-031-19830-4BibTeX
@inproceedings{panagiotakopoulos2022eccv-online,
title = {{Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions}},
author = {Panagiotakopoulos, Theodoros and Dovesi, Pier Luigi and Härenstam-Nielsen, Linus and Poggi, Matteo},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19830-4},
url = {https://mlanthology.org/eccv/2022/panagiotakopoulos2022eccv-online/}
}