Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 6558-6566
Abstract
Semantic segmentation's performance is often compromised when applied to unlabeled adverse weather conditions. Unsupervised domain adaptation is a potential approach to enhancing the model's adaptability and robustness to adverse weather. However, existing methods encounter difficulties when sequentially adapting the model to multiple unlabeled adverse weather conditions. They struggle to acquire new knowledge while also retaining previously learned knowledge. To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudo-label blending, and weather composition replay. Our adaptive knowledge acquisition enables the model to avoid learning from extreme images that could potentially cause the model to forget. In our approach of blending pseudo-labels, we not only utilize the current model but also integrate the previously learned model into the ongoing learning process. This collaboration between the current teacher and the previous model enhances the robustness of the pseudo-labels for the current target. Our weather composition replay mechanism allows the model to continuously refine its previously learned weather information while simultaneously learning from the new target domain. Our method consistently outperforms the state-of-the-art methods, and obtains the best performance with averaged mIoU (%) of 65.7 and the lowest forgetting (%) of 3.6 against 60.1 and 11.3, on the ACDC datsets for a four-target continual multi-target domain adaptation.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Neighborhood-based credibility anchor learning for universal domain adaptationPattern Recognition, 2023
- Scale-Aware Domain Adaptive Faster R-CNNInternational Journal of Computer Vision, 2021
- Single-Image Real-Time Rain Removal Based on Depth-Guided Non-Local FeaturesIEEE Transactions on Image Processing, 2021
- Unsupervised Multi-Target Domain Adaptation: An Information Theoretic ApproachIEEE Transactions on Image Processing, 2020
- Semantic Foggy Scene Understanding with Synthetic DataInternational Journal of Computer Vision, 2018
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017