Weakly Supervised Semantic Segmentation via Mamba Image Restoration

Weakly Supervised Semantic Segmentation (WSSS) aims to achieve pixel-level segmentation using easily annotated weak labels to reduce annotation costs. However, existing WSSS methods typically rely on CAM (Class Activation Maps) as an intermediate segmentation step. The concentrated activation regions of CAM limit the final segmentation performance. To address this issue, we treat the CAMs obtained through traditional methods as low-quality images to be restored and design an image restoration method based on the mamba model. This method expands the activation regions guided by the multi-stage CAMs we extract. Extensive experiments conducted on the PASCAL VOC 2012 and MS COCO 2014 segmentation datasets demonstrate that our approach effectively improves the quality of CAMs and significantly enhances the final segmentation performance. Our segmentation performance is very close to the recent state-of-the-art, which proves the effectiveness of our method.