Self-supervised learning with consistency loss for improving GANs

Jie Gao; Dandan Song

doi:10.1117/12.2652224

10 November 2022 Self-supervised learning with consistency loss for improving GANs

Jie Gao, Dandan Song

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123312Z (2022) https://doi.org/10.1117/12.2652224
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

After much research and advancements, GANs have achieved great success but still face many challenges. In this paper, we adopt self-supervised learning based on rotation angles to overcome the catastrophic forgetting of the discriminator. Self-supervision encourages the discriminator to learn meaningful feature representations that are not forgotten during training. Meanwhile, this paper adopts consistent adversarial training to alleviate the mode collapse of the generator. The consistency constraint condition encourages the discriminator to explore more features, which helps the generator achieve more significant improvement space. This deep generative model improves unsupervised image generation tasks by simultaneously alleviating two critical issues in GANs. Experimental results demonstrate that our model achieves competitive scores.

Citation Download Citation

Jie Gao and Dandan Song "Self-supervised learning with consistency loss for improving GANs", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123312Z (10 November 2022); https://doi.org/10.1117/12.2652224

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

Includes PDF, HTML & Video, when available