Weakly-Supervised Semantic Segmentation via Label Re-assignment in Dual-View Framework

Mining accurate Class Activation Maps (CAMs) is essential for Weakly-Supervised Semantic Segmentation (WSSS). However, the CAMs only activate the most discriminative semantic regions, which can severely affect the segmentation results. Motivated by the observation that local image can capture more details, we propose a Dual-view Label Re-assignment (DLR) framework aiming at the problems of incomplete objects and unclear boundaries in pseudo-labels. Specifically, we first extract comprehensive features and intricate features from global views and local views. In order to take advantage of these features, we further incorporate two additional components, Local View Constraint (LVC) and Foreground-Background Contrast (FBC). LVC facilitates the complementary learning of global and local features through feature transfer loss. FBC enhances boundaries by intensifying the distinction between foreground and background. Experiments show the DLR achieve 1.5% and 3.9% mIoU improvements compared with other method on the validation set of PASCAL VOC 2012 and MS COCO 2014, respectively.