4 papers
Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
Yuhang Zhang, Zhengyu Zhang, Muxin Liao +4
Generalizable semantic segmentation aims to perform well on unseen target domains, a critical challenge due to real-world applications requiring high generalizability. Class-wise p…
Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentation
Binbin Wei, Yuhang Zhang, Shishun Tian +3
Unsupervised Domain Adaptation (UDA) aims to align source and target domain distributions to close the domain gap, but still struggles with obtaining the target data. Fortunately,…
Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation
Muxin Liao, Shishun Tian, Yuhang Zhang +3
Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-invariant features recently. These methods are based on the assumption that the prototypes,…
A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation
Yuhang Zhang, Shishun Tian, Muxin Liao +3
Video semantic segmentation (VSS) is beneficial for dealing with dynamic scenes due to the continuous property of the real-world environment. On the one hand, some methods alleviat…