# Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

arXiv: https://arxiv.org/abs/2108.01070 · HTML: https://mlsanity.com/paper/2108.01070/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 53 references that are in the map.
- First posted on arXiv 2 Aug 2021.

## Builds on (most cited first, 30 of 41)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)

## Built on by (most cited first, 26 of 26)

- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Controlling Vision-Language Models for Multi-Task Image Restoration](https://mlsanity.com/paper/2310.01018/) (2023)
- [Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model](https://mlsanity.com/paper/2403.11157/) (2024)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [Prompt-In-Prompt Learning for Universal Image Restoration](https://mlsanity.com/paper/2312.05038/) (2023)
- [Reflash Dropout in Image Super-Resolution](https://mlsanity.com/paper/2112.12089/) (2021)
- [DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models](https://mlsanity.com/paper/2307.02457/) (2023)
- [Improving Image Restoration through Removing Degradations in Textual Representations](https://mlsanity.com/paper/2312.17334/) (2023)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)
- [Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration](https://mlsanity.com/paper/2409.19403/) (2024)
- [RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization](https://mlsanity.com/paper/2205.05671/) (2022)
- [Networks are Slacking Off: Understanding Generalization Problem in Image Deraining](https://mlsanity.com/paper/2305.15134/) (2023)
- [UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity](https://mlsanity.com/paper/2412.20157/) (2024)
- [Online Video Super-Resolution with Convolutional Kernel Bypass Graft](https://mlsanity.com/paper/2208.02470/) (2022)
- [Meta-Learning based Degradation Representation for Blind Super-Resolution](https://mlsanity.com/paper/2207.13963/) (2022)
- [Interpreting Low-level Vision Models with Causal Effect Maps](https://mlsanity.com/paper/2407.19789/) (2024)
- [Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors](https://mlsanity.com/paper/2307.10667/) (2023)
- [Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining](https://mlsanity.com/paper/2502.12600/) (2025)
- [Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration](https://mlsanity.com/paper/2408.01099/) (2024)
- [Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation](https://mlsanity.com/paper/2205.06891/) (2022)
- [ConStyle v2: A Strong Prompter for All-in-One Image Restoration](https://mlsanity.com/paper/2406.18242/) (2024)
- [Kernelized Back-Projection Networks for Blind Super Resolution](https://mlsanity.com/paper/2302.08478/) (2023)
- [LIR: A Lightweight Baseline for Image Restoration](https://mlsanity.com/paper/2402.01368/) (2024)
- [IRConStyle: Image Restoration Framework Using Contrastive Learning and Style Transfer](https://mlsanity.com/paper/2402.15784/) (2024)
- [RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration](https://mlsanity.com/paper/2509.12039/) (2025)
- [Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients](https://mlsanity.com/paper/2609.38591/) (2026)

## Abstract (arXiv)

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%) discriminative filters for each 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.