# Interpreting Super-Resolution Networks with Local Attribution Maps

arXiv: https://arxiv.org/abs/2011.11036 · HTML: https://mlsanity.com/paper/2011.11036/

## Key facts

- Cited by 136 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2020.

## Built on by (most cited first, 30 of 136)

- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [Rethinking Alignment in Video Super-Resolution Transformers](https://mlsanity.com/paper/2207.08494/) (2022)
- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [On Efficient Transformer-Based Image Pre-training for Low-Level Vision](https://mlsanity.com/paper/2112.10175/) (2021)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution](https://mlsanity.com/paper/2302.13800/) (2023)
- [Masked Image Training for Generalizable Deep Image Denoising](https://mlsanity.com/paper/2303.13132/) (2023)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [Super-Resolution Neural Operator](https://mlsanity.com/paper/2303.02584/) (2023)
- [Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2405.04964/) (2024)
- [MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space](https://mlsanity.com/paper/2405.16105/) (2024)
- [HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution](https://mlsanity.com/paper/2407.05878/) (2024)
- [Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment](https://mlsanity.com/paper/2108.07948/) (2021)
- [Reflash Dropout in Image Super-Resolution](https://mlsanity.com/paper/2112.12089/) (2021)
- [DRCT: Saving Image Super-resolution away from Information Bottleneck](https://mlsanity.com/paper/2404.00722/) (2024)
- [Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2109.02079/) (2021)
- [Multi-scale Attention Network for Single Image Super-Resolution](https://mlsanity.com/paper/2209.14145/) (2022)
- [Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution](https://mlsanity.com/paper/2108.01070/) (2021)
- [AID: Attention Interpolation of Text-to-Image Diffusion](https://mlsanity.com/paper/2403.17924/) (2024)
- [Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution](https://mlsanity.com/paper/2302.08058/) (2023)
- [Attention in Attention Network for Image Super-Resolution](https://mlsanity.com/paper/2104.09497/) (2021)
- [Discovering Distinctive "Semantics" in Super-Resolution Networks](https://mlsanity.com/paper/2108.00406/) (2021)
- [Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration](https://mlsanity.com/paper/2409.19403/) (2024)

## Abstract (arXiv)

Image super-resolution (SR) techniques have been developing rapidly, benefiting from the invention of deep networks and its successive breakthroughs. However, it is acknowledged that deep learning and deep neural networks are difficult to interpret. SR networks inherit this mysterious nature and little works make attempt to understand them. In this paper, we perform attribution analysis of SR networks, which aims at finding the input pixels that strongly influence the SR results. We propose a novel attribution approach called local attribution map (LAM), which inherits the integral gradient method yet with two unique features. One is to use the blurred image as the baseline input, and the other is to adopt the progressive blurring function as the path function. Based on LAM, we show that: (1) SR networks with a wider range of involved input pixels could achieve better performance. (2) Attention networks and non-local networks extract features from a wider range of input pixels. (3) Comparing with the range that actually contributes, the receptive field is large enough for most deep networks. (4) For SR networks, textures with regular stripes or grids are more likely to be noticed, while complex semantics are difficult to utilize. Our work opens new directions for designing SR networks and interpreting low-level vision deep models.