Rectifier Neural Network with a Dual-Pathway Architecture for Image Denoising

09/10/2016
by   Keting Zhang, et al.
0

Recently deep neural networks based on tanh activation function have shown their impressive power in image denoising. In this letter, we try to use rectifier function instead of tanh and propose a dual-pathway rectifier neural network by combining two rectifier neurons with reversed input and output weights in the same hidden layer. We drive the equivalent activation function and compare it to some typical activation functions for image denoising under the same network architecture. The experimental results show that our model achieves superior performances faster especially when the noise is small.

READ FULL TEXT

page 2

page 3

research
01/28/2019

Activation Adaptation in Neural Networks

Many neural network architectures rely on the choice of the activation f...
research
06/08/2023

Normalization-Equivariant Neural Networks with Application to Image Denoising

In many information processing systems, it may be desirable to ensure th...
research
05/17/2020

Separation of Memory and Processing in Dual Recurrent Neural Networks

We explore a neural network architecture that stacks a recurrent layer a...
research
01/05/2023

WIRE: Wavelet Implicit Neural Representations

Implicit neural representations (INRs) have recently advanced numerous v...
research
06/08/2019

Convolutional Bipartite Attractor Networks

In human perception and cognition, the fundamental operation that brains...
research
09/12/2013

Modeling Based on Elman Wavelet Neural Network for Class-D Power Amplifiers

In Class-D Power Amplifiers (CDPAs), the power supply noise can intermod...
research
05/18/2023

NODE-ImgNet: a PDE-informed effective and robust model for image denoising

Inspired by the traditional partial differential equation (PDE) approach...

Please sign up or login with your details

Forgot password? Click here to reset