1 code implementation • 25 Sep 2023 • Muxin Liao, Shishun Tian, Yuhang Zhang, Guoguang Hua, Wenbin Zou, Xia Li
Based on these observations, a calibration-based dual prototypical contrastive learning (CDPCL) approach is proposed to reduce the domain discrepancy between the learned class-wise features and the prototypes of different domains for domain generalization semantic segmentation.
no code implementations • 29 Dec 2022 • Yuhang Zhang, Shishun Tian, Muxin Liao, Zhengyu Zhang, Wenbin Zou, Chen Xu
In this paper, we propose a class-wise non-salient region generalized (CNSG) framework for the VGSS task.