Weakly Supervised Semantic Segmentation by Iterative Superpixel-CRF Refinement with Initial Clues Guiding

•We propose an effective method to generate class-specific attention map. By introducing the concept of spatial class score, our attention map retains more accurate object location clues.•We propose a superpixel-CRF model to refine the segmentation masks for training images. We apply superpixels to recover object boundaries and design a new energy function to obtain high-quality segmentation masks.•We propose an iterative training framework which iteratively refines pixel-level annotations (segmentation masks) and trains the segmentation network to achieve better image segmentation performance.•Our method shows impressive performance, and achieves the state-of-the-art results on PASCAL VOC 2012 dataset and MS COCO dataset compared with existing approaches.