DeepAI AI Chat
Log In Sign Up

Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

by   Luming Liang, et al.
Nanjing University of Aeronautics and Astronautics

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully convolutional deep neural networks, we develop an end-to-end network that removes the extremely high-level s&p noise without performing any non-trivial preprocessing tasks, which is different from all the existing literature in s&p noise removal. Experiments show that inserting median layers into a simple fully-convolutional network with the L2 loss significantly boosts the signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data. The source code has been released for public evaluation and use (


page 1

page 4

page 5

page 7

page 8


End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks

When taking photos in dim-light environments, due to the small amount of...

Training a Fully Convolutional Neural Network to Route Integrated Circuits

We present a deep, fully convolutional neural network that learns to rou...

Detecting and interpreting myocardial infarctions using fully convolutional neural networks

We consider the detection of myocardial infarction in electrocardiograph...

Convolutional Neural Networks for Aircraft Noise Monitoring

Air travel is one of the fastest growing modes of transportation, howeve...

How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning

Recent work suggests that changing Convolutional Neural Network (CNN) ar...

Median Shapes

We introduce and begin to explore the mean and median of finite sets of ...