# Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution

arXiv: https://arxiv.org/abs/2105.03939 · HTML: https://mlsanity.com/paper/2105.03939/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 54 references that are in the map.
- First posted on arXiv 9 May 2021.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (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)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (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)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Residual Feature Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2009.11551/) (2020)
- [Fast and Accurate Single Image Super-Resolution via Information Distillation Network](https://mlsanity.com/paper/1803.09454/) (2018)
- [Structure-Preserving Super Resolution with Gradient Guidance](https://mlsanity.com/paper/2003.13081/) (2020)
- [Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2003.07018/) (2020)
- [Efficient Image Super-Resolution Using Pixel Attention](https://mlsanity.com/paper/2010.01073/) (2020)
- [Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search](https://mlsanity.com/paper/1901.07261/) (2019)
- [MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation](https://mlsanity.com/paper/2003.12238/) (2020)
- [Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution](https://mlsanity.com/paper/1809.11130/) (2018)
- [Efficient Residual Dense Block Search for Image Super-Resolution](https://mlsanity.com/paper/1909.11409/) (2019)
- [AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2009.06943/) (2020)
- [Journey Towards Tiny Perceptual Super-Resolution](https://mlsanity.com/paper/2007.04356/) (2020)

## Built on by (most cited first, 5 of 5)

- [QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise](https://mlsanity.com/paper/2208.14839/) (2022)
- [Outlier-Aware Post-Training Quantization for Image Super-Resolution](https://mlsanity.com/paper/2511.00682/) (2025)
- [Automated Dominative Subspace Mining for Efficient Neural Architecture Search](https://mlsanity.com/paper/2210.17180/) (2022)
- [Deep 3D World Models for Multi-Image Super-Resolution Beyond Optical Flow](https://mlsanity.com/paper/2401.16972/) (2024)
- [Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking](https://mlsanity.com/paper/2402.16570/) (2024)

## Abstract (arXiv)

Single Image Super-Resolution (SISR) tasks have achieved significant performance with deep neural networks. However, the large number of parameters in CNN-based met-hods for SISR tasks require heavy computations. Although several efficient SISR models have been recently proposed, most are handcrafted and thus lack flexibility. In this work, we propose a novel differentiable Neural Architecture Search (NAS) approach on both the cell-level and network-level to search for lightweight SISR models. Specifically, the cell-level search space is designed based on an information distillation mechanism, focusing on the combinations of lightweight operations and aiming to build a more lightweight and accurate SR structure. The network-level search space is designed to consider the feature connections among the cells and aims to find which information flow benefits the cell most to boost the performance. Unlike the existing Reinforcement Learning (RL) or Evolutionary Algorithm (EA) based NAS methods for SISR tasks, our search pipeline is fully differentiable, and the lightweight SISR models can be efficiently searched on both the cell-level and network-level jointly on a single GPU. Experiments show that our methods can achieve state-of-the-art performance on the benchmark datasets in terms of PSNR, SSIM, and model complexity with merely 68G Multi-Adds for × 2 and 18G Multi-Adds for × 4 SR tasks.