Weakly-Supervised Image Semantic Segmentation Using Gaph Convolutional Networks

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.

Weakly-Supervised Image Semantic Segmentation Using Gaph Convolutional Networks, S. Y. Pan, C. Y. Lu, S. P. Lee, and W. H. Pen, ICME, 2021. [PDF|Code]

@inproceedings{pan2021all,
 title={Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks},
 author={Shun-Yi Pan, Cheng-You Lu, Shih-Po Lee, and Wen-Hsiao Peng},
 booktitle={IEEE International Conference on Multimedia and Expo (ICME)},
 year={2021}}