Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentation

arXiv:2404.13701v1 Announce Type: cross
Abstract: Domain generalized semantic segmentation is an essential computer vision task, for which models only leverage source data to learn the capability of generalized semantic segmentation towards the unseen target domains. Previous works typically address this challenge by global style randomization or feature regularization. In this paper, we argue that given the observation that different local semantic regions perform different visual characteristics from the source domain to the target domain, methods focusing on global operations are …

abstract alignment arxiv capability challenge computer computer vision cs.cv cs.lg data domain domains feature generalized global learn paper randomization regularization segmentation semantic source data style type vision