Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention

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, pseudolabel 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 stateof-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 datasets for a four-target continual multi-target domain adaptation.

References in corpus (11)

• Unsupervised Domain Adaptation by Backpropagation
• Domain Agnostic Learning with Disentangled Representations
• ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation
• MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
• Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
• ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
• Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions
• Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation
• VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions