Share Email Print

Journal of Applied Remote Sensing • new

Translation-aware semantic segmentation via conditional least-square generative adversarial networks
Author(s): Mi Zhang; Xiangyun Hu; Like Zhao; Shiyan Pang; Jinqi Gong; Min Luo
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Semantic segmentation has recently made rapid progress in the field of remote sensing and computer vision. However, many leading approaches cannot simultaneously translate label maps to possible source images with a limited number of training images. The core issue is insufficient adversarial information to interpret the inverse process and proper objective loss function to overcome the vanishing gradient problem. We propose the use of conditional least squares generative adversarial networks (CLS-GAN) to delineate visual objects and solve these problems. We trained the CLS-GAN network for semantic segmentation to discriminate dense prediction information either from training images or generative networks. We show that the optimal objective function of CLS-GAN is a special class of f -divergence and yields a generator that lies on the decision boundary of discriminator that reduces possible vanished gradient. We also demonstrate the effectiveness of the proposed architecture at translating images from label maps in the learning process. Experiments on a limited number of high resolution images, including close-range and remote sensing datasets, indicate that the proposed method leads to the improved semantic segmentation accuracy and can simultaneously generate high quality images from label maps.

Paper Details

Date Published: 23 December 2017
PDF: 15 pages
J. Appl. Rem. Sens. 11(4) 042622 doi: 10.1117/1.JRS.11.042622
Published in: Journal of Applied Remote Sensing Volume 11, Issue 4
Show Author Affiliations
Mi Zhang, Wuhan Univ. (China)
Xiangyun Hu, Wuhan Univ. (China)
Like Zhao, Wuhan Univ. (China)
Shiyan Pang, Wuhan Univ. (China)
Jinqi Gong, Wuhan Univ. (China)
Min Luo, Wuhan Univ. (China)

© SPIE. Terms of Use
Back to Top