On Unsupervised Image-to-image translation and GAN stability

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: AlAila, BahaaEddin, Jandaghi, Zahra, Farahani, Abolfazl, Al-Saad, Mohammad Ziad
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911798399074304
author AlAila, BahaaEddin
Jandaghi, Zahra
Farahani, Abolfazl
Al-Saad, Mohammad Ziad
author_facet AlAila, BahaaEddin
Jandaghi, Zahra
Farahani, Abolfazl
Al-Saad, Mohammad Ziad
contents The problem of image-to-image translation is one that is intruiging and challenging at the same time, for the impact potential it can have on a wide variety of other computer vision applications like colorization, inpainting, segmentation and others. Given the high-level of sophistication needed to extract patterns from one domain and successfully applying them to another, especially, in a completely unsupervised (unpaired) manner, this problem has gained much attention as of the last few years. It is one of the first problems where successful applications to deep generative models, and especially Generative Adversarial Networks achieved astounding results that are actually of realworld impact, rather than just a show of theoretical prowess; the such that has been dominating the GAN world. In this work, we study some of the failure cases of a seminal work in the field, CycleGAN [1] and hypothesize that they are GAN-stability related, and propose two general models to try to alleviate these problems. We also reach the same conclusion of the problem being ill-posed that has been also circulating in the literature lately.
format Preprint
id arxiv_https___arxiv_org_abs_2403_09646
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Unsupervised Image-to-image translation and GAN stability
AlAila, BahaaEddin
Jandaghi, Zahra
Farahani, Abolfazl
Al-Saad, Mohammad Ziad
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image and Video Processing
The problem of image-to-image translation is one that is intruiging and challenging at the same time, for the impact potential it can have on a wide variety of other computer vision applications like colorization, inpainting, segmentation and others. Given the high-level of sophistication needed to extract patterns from one domain and successfully applying them to another, especially, in a completely unsupervised (unpaired) manner, this problem has gained much attention as of the last few years. It is one of the first problems where successful applications to deep generative models, and especially Generative Adversarial Networks achieved astounding results that are actually of realworld impact, rather than just a show of theoretical prowess; the such that has been dominating the GAN world. In this work, we study some of the failure cases of a seminal work in the field, CycleGAN [1] and hypothesize that they are GAN-stability related, and propose two general models to try to alleviate these problems. We also reach the same conclusion of the problem being ill-posed that has been also circulating in the literature lately.
title On Unsupervised Image-to-image translation and GAN stability
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2403.09646