Supervised Neural Discrete Universal Denoiser for Adaptive Denoising

TL;DR

This paper enhances Neural DUDE by integrating supervised pre-training with adaptive fine-tuning, significantly improving denoising performance and robustness across diverse datasets like images and DNA sequences.

Contribution

It introduces a combined supervised and adaptive training framework for Neural DUDE, improving scalability, robustness, and performance in discrete denoising tasks.

Findings

Significant performance boost over vanilla Neural DUDE.

Robustness to noise mismatch and blind training.

Effective on diverse datasets like images and DNA sequences.

Abstract

We improve the recently developed Neural DUDE, a neural network-based adaptive discrete denoiser, by combining it with the supervised learning framework. Namely, we make the supervised pre-training of Neural DUDE compatible with the adaptive fine-tuning of the parameters based on the given noisy data subject to denoising. As a result, we achieve a significant denoising performance boost compared to the vanilla Neural DUDE, which only carries out the adaptive fine-tuning step with randomly initialized parameters. Moreover, we show the adaptive fine-tuning makes the algorithm robust such that a noise-mismatched or blindly trained supervised model can still achieve the performance of that of the matched model. Furthermore, we make a few algorithmic advancements to make Neural DUDE more scalable and deal with multi-dimensional data or data with larger alphabet size. We systematically show our improvements on two very diverse datasets, binary images and DNA sequences.