Skip to yearly menu bar Skip to main content


Poster

Neural Universal Discrete Denoiser

Taesup Moon · Seonwoo Min · Byunghan Lee · Sungroh Yoon

Area 5+6+7+8 #108

Keywords: [ Deep Learning or Neural Networks ] [ Information Theory ] [ (Other) Unsupervised Learning Methods ] [ (Application) Signal and Speech Processing ]


Abstract:

We present a new framework of applying deep neural networks (DNN) to devise a universal discrete denoiser. Unlike other approaches that utilize supervised learning for denoising, we do not require any additional training data. In such setting, while the ground-truth label, i.e., the clean data, is not available, we devise ``pseudo-labels'' and a novel objective function such that DNN can be trained in a same way as supervised learning to become a discrete denoiser. We experimentally show that our resulting algorithm, dubbed as Neural DUDE, significantly outperforms the previous state-of-the-art in several applications with a systematic rule of choosing the hyperparameter, which is an attractive feature in practice.

Live content is unavailable. Log in and register to view live content