AdaDM: Enabling Normalization for Image Super-Resolution

by   Jie Liu, et al.

Normalization like Batch Normalization (BN) is a milestone technique to normalize the distributions of intermediate layers in deep learning, enabling faster training and better generalization accuracy. However, in fidelity image Super-Resolution (SR), it is believed that normalization layers get rid of range flexibility by normalizing the features and they are simply removed from modern SR networks. In this paper, we study this phenomenon quantitatively and qualitatively. We found that the standard deviation of the residual feature shrinks a lot after normalization layers, which causes the performance degradation in SR networks. Standard deviation reflects the amount of variation of pixel values. When the variation becomes smaller, the edges will become less discriminative for the network to resolve. To address this problem, we propose an Adaptive Deviation Modulator (AdaDM), in which a modulation factor is adaptively predicted to amplify the pixel deviation. For better generalization performance, we apply BN in state-of-the-art SR networks with the proposed AdaDM. Meanwhile, the deviation amplification strategy in AdaDM makes the edge information in the feature more distinguishable. As a consequence, SR networks with BN and our AdaDM can get substantial performance improvements on benchmark datasets. Extensive experiments have been conducted to show the effectiveness of our method.



page 1

page 8

page 10


Wide Activation for Efficient and Accurate Image Super-Resolution

In this report we demonstrate that with same parameters and computationa...

CT-SRCNN: Cascade Trained and Trimmed Deep Convolutional Neural Networks for Image Super Resolution

We propose methodologies to train highly accurate and efficient deep con...

FAN: Frequency Aggregation Network for Real Image Super-resolution

Single image super-resolution (SISR) aims to recover the high-resolution...

Iterative Network for Image Super-Resolution

Single image super-resolution (SISR), as a traditional ill-conditioned i...

Component Divide-and-Conquer for Real-World Image Super-Resolution

In this paper, we present a large-scale Diverse Real-world image Super-R...

Multi-grained Attention Networks for Single Image Super-Resolution

Deep Convolutional Neural Networks (CNN) have drawn great attention in i...

RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization

This paper explores training efficient VGG-style super-resolution (SR) n...

Code Repositories


AdaDM: Enabling Normalization for Image Super-Resolution

view repo
This week in AI

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