# How Powerful Potential of Attention on Image Restoration?

arXiv: https://arxiv.org/abs/2403.10336 · HTML: https://mlsanity.com/paper/2403.10336/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 77 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 30 of 55)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018)
- [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021)

## Built on by (most cited first, 1 of 1)

- [Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks](https://mlsanity.com/paper/2406.00721/) (2024)

## Abstract (arXiv)

Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-attention and feed-forward network (FFN). The former captures long-range pixel dependencies, while the latter enables the model to learn complex patterns and relationships in the data. Previous studies have demonstrated that FFNs are key-value memories citegeva2020transformer, which are vital in modern Transformer architectures. In this paper, we conduct an empirical study to explore the potential of attention mechanisms without using FFN and provide novel structures to demonstrate that removing FFN is flexible for image restoration. Specifically, we propose Continuous Scaling Attention (CSAttn), a method that computes attention continuously in three stages without using FFN. To achieve competitive performance, we propose a series of key components within the attention. Our designs provide a closer look at the attention mechanism and reveal that some simple operations can significantly affect the model performance. We apply our CSAttn to several image restoration tasks and show that our model can outperform CNN-based and Transformer-based image restoration approaches.