DeepAI AI Chat
Log In Sign Up

Revisiting RCAN: Improved Training for Image Super-Resolution

by   Zudi Lin, et al.
Harvard University

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


page 6

page 13


Residual Local Feature Network for Efficient Super-Resolution

Deep learning based approaches has achieved great performance in single ...

Towards Compact Single Image Super-Resolution via Contrastive Self-distillation

Convolutional neural networks (CNNs) are highly successful for super-res...

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

Lightweight and efficiency are critical drivers for the practical applic...

Anchor-based Plain Net for Mobile Image Super-Resolution

Along with the rapid development of real-world applications, higher requ...

Enhanced Object Detection in Floor-plan through Super Resolution

Building Information Modelling (BIM) software use scalable vector format...

Bicubic++: Slim, Slimmer, Slimmest – Designing an Industry-Grade Super-Resolution Network

We propose a real-time and lightweight single-image super-resolution (SR...

Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution

The field of image super-resolution (SR) has witnessed extensive neural ...

Code Repositories


Revisiting RCAN: Improved Training for Image Super-Resolution

view repo