Saved in:
Bibliographic Details
Main Authors: Waida, Hiroki, Yamazaki, Kimihiro, Tokuhisa, Atsushi, Wada, Mutsuyo, Wada, Yuichiro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.01124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912157347610624
author Waida, Hiroki
Yamazaki, Kimihiro
Tokuhisa, Atsushi
Wada, Mutsuyo
Wada, Yuichiro
author_facet Waida, Hiroki
Yamazaki, Kimihiro
Tokuhisa, Atsushi
Wada, Mutsuyo
Wada, Yuichiro
contents Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.
format Preprint
id arxiv_https___arxiv_org_abs_2405_01124
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Investigating Self-Supervised Image Denoising with Denaturation
Waida, Hiroki
Yamazaki, Kimihiro
Tokuhisa, Atsushi
Wada, Mutsuyo
Wada, Yuichiro
Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
Statistics Theory
Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.
title Investigating Self-Supervised Image Denoising with Denaturation
topic Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
Statistics Theory
url https://arxiv.org/abs/2405.01124