EXPLORING CATEGORY CONSISTENCY FOR WEAKLY SUPERVISED SEMANTIC SEGMENTATION

Self-supervised framework has been widely used in weakly supervised semantic segmentation. Generating a reliable and detailed pseudo mask label is the main challenge for improving the quality of predicted mask. In this paper, we propose Category Consistency Mask Refinement (CCMR) to explore the category consistency cued with the input image, and inject such information to mask refinement, guaranteeing the completeness of the refined mask. Moreover, we exploit Selective Weighted Pooling (SWP) to restrict the backward propagation of background, limiting the update of the background. Experimental results demonstrate that our methods can boost the performance on the PASCAL VOC 2012 segmentation benchmark, outperforming the state-of-the-art weakly supervised semantic segmentation methods.