Analyzing and Improving Optimal-Transport-based Adversarial Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Jaemoo, Choi, Jaewoong, Kang, Myungjoo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866907823764406272
author Choi, Jaemoo
Choi, Jaewoong
Kang, Myungjoo
author_facet Choi, Jaemoo
Choi, Jaewoong
Kang, Myungjoo
contents Optimal Transport (OT) problem aims to find a transport plan that bridges two distributions while minimizing a given cost function. OT theory has been widely utilized in generative modeling. In the beginning, OT distance has been used as a measure for assessing the distance between data and generated distributions. Recently, OT transport map between data and prior distributions has been utilized as a generative model. These OT-based generative models share a similar adversarial training objective. In this paper, we begin by unifying these OT-based adversarial methods within a single framework. Then, we elucidate the role of each component in training dynamics through a comprehensive analysis of this unified framework. Moreover, we suggest a simple but novel method that improves the previously best-performing OT-based model. Intuitively, our approach conducts a gradual refinement of the generated distribution, progressively aligning it with the data distribution. Our approach achieves a FID score of 2.51 on CIFAR-10 and 5.99 on CelebA-HQ-256, outperforming unified OT-based adversarial approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2310_02611
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Analyzing and Improving Optimal-Transport-based Adversarial Networks
Choi, Jaemoo
Choi, Jaewoong
Kang, Myungjoo
Machine Learning
Computer Vision and Pattern Recognition
Optimal Transport (OT) problem aims to find a transport plan that bridges two distributions while minimizing a given cost function. OT theory has been widely utilized in generative modeling. In the beginning, OT distance has been used as a measure for assessing the distance between data and generated distributions. Recently, OT transport map between data and prior distributions has been utilized as a generative model. These OT-based generative models share a similar adversarial training objective. In this paper, we begin by unifying these OT-based adversarial methods within a single framework. Then, we elucidate the role of each component in training dynamics through a comprehensive analysis of this unified framework. Moreover, we suggest a simple but novel method that improves the previously best-performing OT-based model. Intuitively, our approach conducts a gradual refinement of the generated distribution, progressively aligning it with the data distribution. Our approach achieves a FID score of 2.51 on CIFAR-10 and 5.99 on CelebA-HQ-256, outperforming unified OT-based adversarial approaches.
title Analyzing and Improving Optimal-Transport-based Adversarial Networks
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.02611