Saved in:
Bibliographic Details
Main Authors: Gong, Yanxiang, Xie, Zhiwei, Duan, Guozhen, Ma, Zheng, Xie, Mei
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2212.01521
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913199716040704
author Gong, Yanxiang
Xie, Zhiwei
Duan, Guozhen
Ma, Zheng
Xie, Mei
author_facet Gong, Yanxiang
Xie, Zhiwei
Duan, Guozhen
Ma, Zheng
Xie, Mei
contents Mode collapse is a significant unsolved issue of generative adversarial networks. In this work, we examine the causes of mode collapse from a novel perspective. Due to the nonuniform sampling in the training process, some sub-distributions may be missed when sampling data. As a result, even when the generated distribution differs from the real one, the GAN objective can still achieve the minimum. To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution. When the generated distribution differs from the real one, GDF will make the objective harder to reach the minimal value, while the original global minimum is not changed. To deal with the circumstance when the overall real data is unreachable, we also propose a local distribution fitting (LDF) method. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.
format Preprint
id arxiv_https___arxiv_org_abs_2212_01521
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks
Gong, Yanxiang
Xie, Zhiwei
Duan, Guozhen
Ma, Zheng
Xie, Mei
Machine Learning
Artificial Intelligence
Mode collapse is a significant unsolved issue of generative adversarial networks. In this work, we examine the causes of mode collapse from a novel perspective. Due to the nonuniform sampling in the training process, some sub-distributions may be missed when sampling data. As a result, even when the generated distribution differs from the real one, the GAN objective can still achieve the minimum. To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution. When the generated distribution differs from the real one, GDF will make the objective harder to reach the minimal value, while the original global minimum is not changed. To deal with the circumstance when the overall real data is unreachable, we also propose a local distribution fitting (LDF) method. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.
title Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2212.01521