Image denoising with multi-layer perceptrons, part 2: training trade-offs and analysis of their mechanisms

TL;DR

This paper analyzes the training trade-offs and mechanisms of multi-layer perceptrons used for image denoising, providing insights into their functioning and guidelines for effective training.

Contribution

It offers a detailed analysis of training trade-offs and activation patterns in MLPs for image denoising, enhancing understanding of their internal mechanisms.

Findings

Effective training strategies for MLPs in denoising

Identification of pitfalls to avoid during training

Insights into activation patterns and their role in denoising

Abstract

Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. In another paper, we show that multi-layer perceptrons can achieve outstanding image denoising performance for various types of noise (additive white Gaussian noise, mixed Poisson-Gaussian noise, JPEG artifacts, salt-and-pepper noise and noise resembling stripes). In this work we discuss in detail which trade-offs have to be considered during the training procedure. We will show how to achieve good results and which pitfalls to avoid. By analysing the activation patterns of the hidden units we are able to make observations regarding the functioning principle of multi-layer perceptrons trained for image denoising.