Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions
This work addresses the challenge of maintaining accuracy in semantic segmentation for autonomous systems under ever-changing conditions, representing an incremental improvement over offline domain adaptation methods.
The paper tackles the problem of adapting semantic segmentation models to continuous and unpredictable domain shifts during deployment, such as sudden weather changes, and demonstrates that their framework effectively adapts to new domains while avoiding catastrophic forgetting.
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.