# Revisiting RCAN: Improved Training for Image Super-Resolution

arXiv: https://arxiv.org/abs/2201.11279 · HTML: https://mlsanity.com/paper/2201.11279/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 55 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [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)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [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)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [Large Batch Training of Convolutional Networks](https://mlsanity.com/paper/1708.03888/) (2017)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)

## Built on by (most cited first, 30 of 32)

- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models](https://mlsanity.com/paper/2304.08291/) (2023)
- [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)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [Residual Local Feature Network for Efficient Super-Resolution](https://mlsanity.com/paper/2205.07514/) (2022)
- [N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.11436/) (2022)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [Multi-scale Attention Network for Single Image Super-Resolution](https://mlsanity.com/paper/2209.14145/) (2022)
- [Guided Depth Map Super-resolution: A Survey](https://mlsanity.com/paper/2302.09598/) (2023)
- [NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results](https://mlsanity.com/paper/2204.09314/) (2022)
- [AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results](https://mlsanity.com/paper/2208.11184/) (2022)
- [MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution](https://mlsanity.com/paper/2404.09571/) (2024)
- [NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results](https://mlsanity.com/paper/2205.12633/) (2022)
- [Activating Wider Areas in Image Super-Resolution](https://mlsanity.com/paper/2403.08330/) (2024)
- [Reciprocal Attention Mixing Transformer for Lightweight Image Restoration](https://mlsanity.com/paper/2305.11474/) (2023)
- [Rethinking Image Super-Resolution from Training Data Perspectives](https://mlsanity.com/paper/2409.00768/) (2024)
- [Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution](https://mlsanity.com/paper/2407.16232/) (2024)
- [Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation](https://mlsanity.com/paper/2205.06891/) (2022)
- [ITSRN++: Stronger and Better Implicit Transformer Network for Continuous Screen Content Image Super-Resolution](https://mlsanity.com/paper/2210.08812/) (2022)
- [Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training](https://mlsanity.com/paper/2304.01805/) (2023)
- [Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging](https://mlsanity.com/paper/2301.01732/) (2023)
- [Image Super-Resolution using Efficient Striped Window Transformer](https://mlsanity.com/paper/2301.09869/) (2023)
- [ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis](https://mlsanity.com/paper/2304.04291/) (2023)
- [Instance Data Condensation for Image Super-Resolution](https://mlsanity.com/paper/2505.21099/) (2025)
- [Your Super Resolution Model is not Enough for Tackling Real-World Scenarios](https://mlsanity.com/paper/2509.06387/) (2025)
- [Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention](https://mlsanity.com/paper/2603.06738/) (2026)
- [Rethinking PRL: A Multiscale Progressively Residual Learning Network for Inverse Halftoning](https://mlsanity.com/paper/2305.17355/) (2023)
- [Revolutionizing Space Health (Swin-FSR): Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology](https://mlsanity.com/paper/2308.06332/) (2023)
- [Lightweight single-image super-resolution network based on dual paths](https://mlsanity.com/paper/2409.06590/) (2024)

## Abstract (arXiv)

Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight. However, most SR models were optimized with dated training strategies. In this work, we revisit the popular RCAN model and examine the effect of different training options in SR. Surprisingly (or perhaps as expected), we show that RCAN can outperform or match nearly all the CNN-based SR architectures published after RCAN on standard benchmarks with a proper training strategy and minimal architecture change. Besides, although RCAN is a very large SR architecture with more than four hundred convolutional layers, we draw a notable conclusion that underfitting is still the main problem restricting the model capability instead of overfitting. We observe supportive evidence that increasing training iterations clearly improves the model performance while applying regularization techniques generally degrades the predictions. We denote our simply revised RCAN as RCAN-it and recommend practitioners to use it as baselines for future research. Code is publicly available at https://github.com/zudi-lin/rcan-it.