Distribution constraining for combating mode collapse in generative adversarial networks

Image synthesis is a critical technique in the image processing field. Recently, generative adversarial networks (GANs) have played a significant role in synthesis tasks. However, the issue of mode collapse remains a major challenge in GANs, which limits their potential applications. We propose a me...

Full description

Saved in:
Bibliographic Details
Published in:Journal of electronic imaging 2023-07, Vol.32 (4), p.043029-043029
Main Authors: Gong, Yanxiang, Zhong, Minjiang, Ji, Yang, Xie, Mei, Ma, Xin
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image synthesis is a critical technique in the image processing field. Recently, generative adversarial networks (GANs) have played a significant role in synthesis tasks. However, the issue of mode collapse remains a major challenge in GANs, which limits their potential applications. We propose a method to address the mode collapse problem. Our approach focuses on minimizing the divergence between the distributions of real and generated features, thereby reducing the learning pressure on the discriminator. An advantage of our method is that it does not require prior knowledge or manual design. Additionally, it can be easily incorporated into state-of-the-art frameworks across various domains. Experimental results demonstrate the effectiveness and competitive performance of our proposed method.
ISSN:1017-9909
1560-229X
DOI:10.1117/1.JEI.32.4.043029