Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

by   Liangbin Xie, et al.

Recent blind super-resolution (SR) methods typically consist of two branches, one for degradation prediction and the other for conditional restoration. However, our experiments show that a one-branch network can achieve comparable performance to the two-branch scheme. Then we wonder: how can one-branch networks automatically learn to distinguish degradations? To find the answer, we propose a new diagnostic tool – Filter Attribution method based on Integral Gradient (FAIG). Unlike previous integral gradient methods, our FAIG aims at finding the most discriminative filters instead of input pixels/features for degradation removal in blind SR networks. With the discovered filters, we further develop a simple yet effective method to predict the degradation of an input image. Based on FAIG, we show that, in one-branch blind SR networks, 1) we are able to find a very small number of (1 specific degradation; 2) The weights, locations and connections of the discovered filters are all important to determine the specific network function. 3) The task of degradation prediction can be implicitly realized by these discriminative filters without explicit supervised learning. Our findings can not only help us better understand network behaviors inside one-branch blind SR networks, but also provide guidance on designing more efficient architectures and diagnosing networks for blind SR.


page 3

page 7

page 9


From General to Specific: Online Updating for Blind Super-Resolution

Most deep learning-based super-resolution (SR) methods are not image-spe...

Kernelized Back-Projection Networks for Blind Super Resolution

Since non-blind Super Resolution (SR) fails to super-resolve Low-Resolut...

The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks

To date, the best-performing blind super-resolution (SR) techniques foll...

Knowledge Distillation based Degradation Estimation for Blind Super-Resolution

Blind image super-resolution (Blind-SR) aims to recover a high-resolutio...

Interpreting Super-Resolution Networks with Local Attribution Maps

Image super-resolution (SR) techniques have been developing rapidly, ben...

Conditional Meta-Network for Blind Super-Resolution with Multiple Degradations

Although single-image super-resolution (SISR) methods have achieved grea...

Please sign up or login with your details

Forgot password? Click here to reset