@inproceedings{655fddb672434a2097d38ec05d7c6f10,
title = "WEAKLY-SUPERVISED IMAGE SEMANTIC SEGMENTATION USING GRAPH CONVOLUTIONAL NETWORKS",
abstract = "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.",
keywords = "Graph Convolutional Networks, Weakly-supervised image semantic segmentation",
author = "Pan, {Shun Yi} and Lu, {Cheng You} and Lee, {Shih Po} and Peng, {Wen Hsiao}",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Conference on Multimedia and Expo, ICME 2021 ; Conference date: 05-07-2021 Through 09-07-2021",
year = "2021",
doi = "10.1109/ICME51207.2021.9428116",
language = "English",
series = "Proceedings - IEEE International Conference on Multimedia and Expo",
publisher = "IEEE Computer Society",
booktitle = "2021 IEEE International Conference on Multimedia and Expo, ICME 2021",
address = "美國",
}