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

arXiv:2212.00621v2 Announce Type: replace
Abstract: Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, 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 …

abstract arxiv cars cases conda continual cs.cv data domain domain adaptation driving perception performance practice segmentation self-driving semantic type unsupervised use cases visual world