Supervised Neural Discrete Universal Denoiser for Adaptive Denoising

Autor:	Cha, Sungmin, Min, Seonwoo, Yoon, Sungroh, Moon, Taesup
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Preprint
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2111.12350 Zobrazit plný text záznamu View this record from Arxiv