Distribution-Aware Continual Test-Time Adaptation for Semantic Segmentation

arXiv:2309.13604v2 Announce Type: replace
Abstract: Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However, the pursuit of long-term adaptation often introduces catastrophic forgetting and error accumulation problems, which impede the practical implementation of CTTA in the real world. Recently, existing CTTA methods mainly focus on utilizing a majority of parameters to fit target domain knowledge through self-training. Unfortunately, these …

abstract arxiv autonomous autonomous driving autonomous driving systems catastrophic forgetting continual cs.ai cs.cv distribution domains driving dynamic environments error face however implementation long-term practical segmentation semantic strategy systems test type