Cited 0 time in webofscience Cited 0 time in scopus

Neural universal discrete denoiser

Title
Neural universal discrete denoiser
Authors
Moon, TaesupMin, SeonwooLee, ByunghanYoon, Sungroh
Issue Date
2016
Citation
30th Annual Conference on Neural Information Processing Systems, NIPS 2016, 4779-4787
Type
Conference
Article Type
Conference Paper
ISSN
1049-5258
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 "pseudolabels" 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. © 2016 NIPS Foundation - All Rights Reserved.
URI
http://hdl.handle.net/20.500.11750/5442
Publisher
Neural information processing systems foundation
Files:
There are no files associated with this item.
Collection:
ETC2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE