Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks
It addresses the problem of reducing annotation costs for semantic segmentation in computer vision, but is incremental as it builds on existing weakly-supervised methods.
This work tackles weakly-supervised image semantic segmentation using image-level labels by proposing a Graph Convolutional Network-based feature propagation framework to generate complete pseudo labels, achieving superior results on the PASCAL VOC 2012 dataset compared to state-of-the-art baselines.
This work addresses weakly-supervised image semantic segmentation based on image-level class labels. One common approach to this task is to propagate the activation scores of Class Activation Maps (CAMs) using a random-walk mechanism in order to arrive at complete pseudo labels for training a semantic segmentation network in a fully-supervised manner. However, the feed-forward nature of the random walk imposes no regularization on the quality of the resulting complete pseudo labels. To overcome this issue, we propose a Graph Convolutional Network (GCN)-based feature propagation framework. We formulate the generation of complete pseudo labels as a semi-supervised learning task and learn a 2-layer GCN separately for every training image by back-propagating a Laplacian and an entropy regularization loss. Experimental results on the PASCAL VOC 2012 dataset confirm the superiority of our scheme to several state-of-the-art baselines. Our code is available at https://github.com/Xavier-Pan/WSGCN.