# Reflash Dropout in Image Super-Resolution

arXiv: https://arxiv.org/abs/2112.12089 · HTML: https://mlsanity.com/paper/2112.12089/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 65 references that are in the map.
- First posted on arXiv 22 Dec 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [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)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [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)
- [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)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [FractalNet: Ultra-Deep Neural Networks without Residuals](https://mlsanity.com/paper/1605.07648/) (2016)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [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)
- [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://mlsanity.com/paper/1908.06382/) (2019)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)

## Built on by (most cited first, 30 of 41)

- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Cross Aggregation Transformer for Image Restoration](https://mlsanity.com/paper/2211.13654/) (2022)
- [Accurate Image Restoration with Attention Retractable Transformer](https://mlsanity.com/paper/2210.01427/) (2022)
- [NAFSSR: Stereo Image Super-Resolution Using NAFNet](https://mlsanity.com/paper/2204.08714/) (2022)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing](https://mlsanity.com/paper/2408.14180/) (2024)
- [MogaNet: Multi-order Gated Aggregation Network](https://mlsanity.com/paper/2211.03295/) (2022)
- [Masked Image Training for Generalizable Deep Image Denoising](https://mlsanity.com/paper/2303.13132/) (2023)
- [MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing](https://mlsanity.com/paper/2302.04501/) (2023)
- [N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.11436/) (2022)
- [Towards Practical Certifiable Patch Defense with Vision Transformer](https://mlsanity.com/paper/2203.08519/) (2022)
- [An Intelligent Agentic System for Complex Image Restoration Problems](https://mlsanity.com/paper/2410.17809/) (2024)
- [Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution](https://mlsanity.com/paper/2305.18107/) (2023)
- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results](https://mlsanity.com/paper/2204.09314/) (2022)
- [Evaluating the Generalization Ability of Super-Resolution Networks](https://mlsanity.com/paper/2205.07019/) (2022)
- [Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration](https://mlsanity.com/paper/2412.00878/) (2024)
- [Networks are Slacking Off: Understanding Generalization Problem in Image Deraining](https://mlsanity.com/paper/2305.15134/) (2023)
- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution](https://mlsanity.com/paper/2309.03020/) (2023)
- [UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic Network](https://mlsanity.com/paper/2209.01809/) (2022)
- [SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge](https://mlsanity.com/paper/2304.12556/) (2023)
- [Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation](https://mlsanity.com/paper/2406.08896/) (2024)
- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [A Preliminary Exploration Towards General Image Restoration](https://mlsanity.com/paper/2408.15143/) (2024)
- [Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining](https://mlsanity.com/paper/2502.12600/) (2025)
- [Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images](https://mlsanity.com/paper/2210.04198/) (2022)
- [SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting](https://mlsanity.com/paper/2307.14489/) (2023)
- [Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution](https://mlsanity.com/paper/2402.18929/) (2024)

## Abstract (arXiv)

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools -- one is from recent network interpretation works, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks.