CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars

Thanh-Dat Truong, Pierce Helton, Ahmed Moustafa, Jackson David Cothren, Khoa Luu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 5642-5650

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation these approaches remain impractical in real-world use cases. In practice the segmentation models may encounter new data that have not been seen yet. Also the previous data training of segmentation models may be inaccessible due to privacy problems. Therefore to address these problems in this work we propose a Continual Unsupervised Domain Adaptation (CONDA) approach that allows the model to continuously learn and adapt with respect to the presence of the new data. Moreover our proposed approach is designed without the requirement of accessing previous training data. To avoid the catastrophic forgetting problem and maintain the performance of the segmentation models we present a novel Bijective Maximum Likelihood loss to impose the constraint of predicted segmentation distribution shifts. The experimental results on the benchmark of continual unsupervised domain adaptation have shown the advanced performance of the proposed CONDA method.