Paper Info
Title
Adaptively Tuning a Convolutional Neural Network by Gate Process for Image Denoising.
Abstract
The conventional image denoising methods based on the convolutional neural network (CNN) focus on the non-blind training, and hence many networks are required to cope with various noise levels at the test. Although there are blind training methods that deal with multiple noise levels with a single network, their performance gain is generally lower than the non-blind ones, especially at low noise levels. In this paper, we propose a new denoising scheme that controls the feature maps of a single denoising network according to the noise level at the test phase, without changing the network parameters. This is achieved by employing a gating scheme where the feature maps of the denoising network are multiplied with appropriate weights from a gate-weight generating network which is trained along with the denoising network. We train the overall network on a wide range of noise level such that the proposed method can be used for both blind and non-blind cases. The experiments show that the proposed system yields better denoising performance than the other CNN-based methods, especially for the untrained noise levels. Finally, it is shown that the proposed system can manage spatially variant unknown noises and real noises without changing the whole CNN parameters.
Year
DOI
Venue
2019
10.1109/ACCESS.2019.2917537
IEEE ACCESS
Keywords
Field
DocType
Denoising,adaptive denoiser,flexible denoiser,convolutional neural network (CNN),noise level estimation,gate-weight generating network
Network on,Noise reduction,Pattern recognition,Convolutional neural network,Computer science,Noise level,Low noise,Image denoising,Artificial intelligence,Distributed computing
Journal
Volume
ISSN
Citations 
7
2169-3536
1
PageRank 
References 
Authors
0.35
0
3
Name
Order
Citations
PageRank
Yoonsik Kim1113.87
Jae Woong Soh2266.76
Nam Ik Cho3712106.98