Investigating Self-Supervised Image Denoising with Denaturation
This provides incremental insights for improving self-supervised image denoising methods in machine learning, particularly for handling noisy data with denaturation.
The paper tackled the problem of self-supervised image denoising with denatured data by analyzing an algorithm theoretically and experimentally, showing it finds desired solutions for population risk and aligns empirical performance with 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.