WEAKLY-SUPERVISED IMAGE SEMANTIC SEGMENTATION USING GRAPH CONVOLUTIONAL NETWORKS

Shun Yi Pan, Cheng You Lu, Shih Po Lee, Wen Hsiao Peng

研究成果: Conference contribution同行評審

30 引文 斯高帕斯(Scopus)

摘要

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.

原文English
主出版物標題2021 IEEE International Conference on Multimedia and Expo, ICME 2021
發行者IEEE Computer Society
ISBN(電子)9781665438643
DOIs
出版狀態Published - 2021
事件2021 IEEE International Conference on Multimedia and Expo, ICME 2021 - Shenzhen, 中國
持續時間: 5 7月 20219 7月 2021

出版系列

名字Proceedings - IEEE International Conference on Multimedia and Expo
ISSN(列印)1945-7871
ISSN(電子)1945-788X

Conference

Conference2021 IEEE International Conference on Multimedia and Expo, ICME 2021
國家/地區中國
城市Shenzhen
期間5/07/219/07/21

指紋

深入研究「WEAKLY-SUPERVISED IMAGE SEMANTIC SEGMENTATION USING GRAPH CONVOLUTIONAL NETWORKS」主題。共同形成了獨特的指紋。

引用此