Investigating Self-Supervised Image Denoising with Denaturation

arXiv:2405.01124v1 Announce Type: cross
Abstract: 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 …

abstract analyze arxiv cs.cv cs.lg data denoising eess.iv however image machine machine learning math.st paper performance self-supervised learning stat.ml stat.th supervised learning type understanding