Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/137189
Title: SURVEY OF DEEP NEURAL NETWORKS IN BLIND DENOISING USING DIFFERENT ARCHITECTURES AND DIFFERENT LABELS
Authors: LOO TIANG KUAN, LEONARD
Keywords: Deep Learning; ResNets; Image Blind Denoising; Backpropagation
Issue Date: 30-Jun-2017
Source: LOO TIANG KUAN, LEONARD (2017-06-30). SURVEY OF DEEP NEURAL NETWORKS IN BLIND DENOISING USING DIFFERENT ARCHITECTURES AND DIFFERENT LABELS. ScholarBank@NUS Repository.
Abstract: This thesis is aimed at providing a better understanding of using deep ConvNets in image denoising. Under a supervised setting, it is intuitive to use the ground truth as the label, and let the ConvNets learn to produce a latent image as the output. However we can also use the noise as its label, and subtract it from the noisy image to obtain the latent image. The first discussion would be the effectiveness and difference between using these two labels. Following that, we experiment between using the traditional ConvNets, and the recent ResNets. Since its introduction, ResNets has become popular due to its performance in the ImageNet competition. Its ability to reduce loss and improve accuracy of classification by simply adding more layers with skip-connections was the main reason for its growing popularity. With this hype, we wish to experiment its effectiveness in the denoising task, and similarly, we aim to examine its performance with using either truth or noise labels. Experimental results allow us to conclude that in terms of training loss, ResNets gives better performance regardless of the type of labels. However, in terms of PSNR for test data, the results are inconclusive, as ConvNets perform better.
URI: http://scholarbank.nus.edu.sg/handle/10635/137189
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
codes.zip10.39 kBZIP

OPEN

NoneView/Download
Neural Network Weights.zip8.66 MBZIP

OPEN

NoneView/Download
Denoised Images.zip95.35 MBZIP

OPEN

NoneView/Download
LooTKL.pdf13.89 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

26
checked on Jan 14, 2018

Download(s)

48
checked on Jan 14, 2018

Google ScholarTM

Check


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