Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks

Abstract: 

Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this paper, we investigate using data augmentation approach to balance the label distribution in order to improve segmentation performance. We propose using generative adversarial networks (GANs) to generate realistic images for improving the performance of semantic segmentation networks. Experimental results show that the proposed method can not only improve segmentation accuracy of those classes with low accuracy,but also obtain 1.3% to 2.1% increase in average segmentation accuracy. It proves that this augmentation method can boost the accuracy and be easily applicable to any other segmentation models.

up
0 users have voted:

Paper Details

Authors:
Shuangting Liu, Jiaqi Zhang, Yuxin Chen, Yifan Liu, Tao Wan
Submitted On:
8 May 2019 - 7:18am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Jiaqi Zhang
Paper Code:
4496
Document Year:
2019
Cite

Document Files

poster of the paper

(40)

Subscribe

[1] Shuangting Liu, Jiaqi Zhang, Yuxin Chen, Yifan Liu, Tao Wan, "Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4071. Accessed: Dec. 15, 2019.
@article{4071-19,
url = {http://sigport.org/4071},
author = {Shuangting Liu; Jiaqi Zhang; Yuxin Chen; Yifan Liu; Tao Wan },
publisher = {IEEE SigPort},
title = {Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks},
year = {2019} }
TY - EJOUR
T1 - Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks
AU - Shuangting Liu; Jiaqi Zhang; Yuxin Chen; Yifan Liu; Tao Wan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4071
ER -
Shuangting Liu, Jiaqi Zhang, Yuxin Chen, Yifan Liu, Tao Wan. (2019). Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks. IEEE SigPort. http://sigport.org/4071
Shuangting Liu, Jiaqi Zhang, Yuxin Chen, Yifan Liu, Tao Wan, 2019. Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks. Available at: http://sigport.org/4071.
Shuangting Liu, Jiaqi Zhang, Yuxin Chen, Yifan Liu, Tao Wan. (2019). "Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks." Web.
1. Shuangting Liu, Jiaqi Zhang, Yuxin Chen, Yifan Liu, Tao Wan. Poster of pixel level data augmentation for semantic image segmentation using generative adversarial networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4071