Share Email Print

Proceedings Paper

Semi-supervised semantic image segmentation using dual discriminator adversarial networks
Author(s): Beibei Liu; Bei Hua
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Semantic image segmentation approaches based on convolutional neural networks require a large amount of pixel-level training data, but the labeling process is time consuming and laborious. In this paper, we propose a semi-supervised semantic segmentation method that can leverage unlabeled data in model training to alleviate the task of labeling. A novel GAN framework comprised of a generator network and a dual discriminator network is proposed, and the entire network is trained by coupling the standard multi-class cross entropy loss with the adversarial loss. To further improve the localization of object boundaries, a self-attention layer is added to the generator network to model long-range dependencies in images, and a skip layer is also added to combine deep layer with highly abstract information and shallow layer with detailed appearance information. The dual discriminator network includes a fully convolutional discriminator and a typical GAN discriminator, so that the input image can be discriminated on both pixel level and image level. For semi-supervised semantic segmentation, the predicted segmentation results of unlabeled images are selected by image-level discriminator, and then their trustworthy regions are generated by pixel-level discriminator to provide additional supervisory signals. Extensive experiments on PASCAL VOC 2012 dataset demonstrate that our approach outperforms existing semi-supervised semantic image segmentation methods on accuracy.

Paper Details

Date Published: 14 August 2019
PDF: 6 pages
Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 1117907 (14 August 2019); doi: 10.1117/12.2539666
Show Author Affiliations
Beibei Liu, Univ. of Science and Technology of China (China)
Bei Hua, Univ. of Science and Technology of China (China)

Published in SPIE Proceedings Vol. 11179:
Eleventh International Conference on Digital Image Processing (ICDIP 2019)
Jenq-Neng Hwang; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?