Dense-Sparse Deep CNN Training for Image Denoising

by   Basit O. Alawode, et al.

Recently, deep learning (DL) methods such as convolutional neural networks (CNNs) have gained prominence in the area of image denoising. This is owing to their proven ability to surpass state-of-the-art classical image denoising algorithms such as BM3D. Deep denoising CNNs (DnCNNs) use many feedforward convolution layers with added regularization methods of batch normalization and residual learning to improve denoising performance significantly. However, this comes at the expense of a huge number of trainable parameters. In this paper, we address this issue by reducing the number of parameters while achieving a comparable level of performance. We derive motivation from the improved performance obtained by training networks using the dense-sparse-dense (DSD) training approach. We extend this training approach to a reduced DnCNN (RDnCNN) network resulting in a faster denoising network with significantly reduced parameters and comparable performance to the DnCNN.



There are no comments yet.


page 4


Enhanced CNN for image denoising

Due to the flexible architectures of deep convolutional neural networks ...

Meta-Optimization of Deep CNN for Image Denoising Using LSTM

The recent application of deep learning (DL) to various tasks has seen t...

Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising

Recent years have witnessed the great success of deep convolutional neur...

Multi-wavelet residual dense convolutional neural network for image denoising

Networks with large receptive field (RF) have shown advanced fitting abi...

User Loss -- A Forced-Choice-Inspired Approach to Train Neural Networks directly by User Interaction

In this paper, we investigate whether is it possible to train a neural n...

A Multiscale Image Denoising Algorithm Based On Dilated Residual Convolution Network

Image denoising is a classical problem in low level computer vision. Mod...

Learning Integrodifferential Models for Image Denoising

We introduce an integrodifferential extension of the edge-enhancing anis...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.