Antimode collapse generative adversarial networks

Yuelong Li; Bowen Li; Zengbin Gao; Jianming Wang

doi:10.1117/1.JEI.28.2.023020

25 March 2019 Antimode collapse generative adversarial networks

Yuelong Li, Bowen Li, Zengbin Gao, Jianming Wang

Author Affiliations +

Funded by: National Natural Science Foundation of China (NSFC), Tianjin Natural Science Foundation, Program for Innovative Research Team in University of Tianjin

Journal of Electronic Imaging, Vol. 28, Issue 2, 023020 (March 2019). https://doi.org/10.1117/1.JEI.28.2.023020

Abstract

Generative adversarial networks (GANs) are a class of techniques widely applied in image synthesis, recovery, compensation, and other related fields. We propose and introduce a novel, improved conditional model antimode collapse GANs (AMCGANs). Through a newly designed network architecture and optimizing strategy, the function of the class label information is moderately constrained and it no longer directly influences the discriminator, and hence the synthesized images belonging to the same classes will not be excessively concentrated due to the attraction of the same labels. Thus, the mode collapse problem, namely generating homogeneity, which always hinders image synthesization approaches can be effectively restrained. On the other hand, by sharing the feature extraction part and only updating its weights during the training of discriminator, AMCGANs achieves relatively efficient computing performance. In addition, it works well both for supervised and for semisupervised learning circumstances. Extensive experiments have been conducted on the Fashion-MNIST and CIFAR10 data sets to verify the effectiveness of the proposed approach.

Citation Download Citation

Yuelong Li, Bowen Li, Zengbin Gao, and Jianming Wang "Antimode collapse generative adversarial networks," Journal of Electronic Imaging 28(2), 023020 (25 March 2019). https://doi.org/10.1117/1.JEI.28.2.023020

Received: 3 August 2018; Accepted: 12 February 2019; Published: 25 March 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE