# Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search

arXiv: https://arxiv.org/abs/1901.07261 · HTML: https://mlsanity.com/paper/1901.07261/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2019.

## Built on by (most cited first, 30 of 66)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution](https://mlsanity.com/paper/2302.13800/) (2023)
- [ShuffleMixer: An Efficient ConvNet for Image Super-Resolution](https://mlsanity.com/paper/2205.15175/) (2022)
- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Self-Calibrated Efficient Transformer for Lightweight Super-Resolution](https://mlsanity.com/paper/2204.08913/) (2022)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution](https://mlsanity.com/paper/2112.04488/) (2021)
- [Edge-enhanced Feature Distillation Network for Efficient Super-Resolution](https://mlsanity.com/paper/2204.08759/) (2022)
- [Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation](https://mlsanity.com/paper/2108.08202/) (2021)
- [MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN](https://mlsanity.com/paper/2107.12679/) (2021)
- [GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search](https://mlsanity.com/paper/2405.20725/) (2024)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [Attentive Fine-Grained Structured Sparsity for Image Restoration](https://mlsanity.com/paper/2204.12266/) (2022)
- [A heterogeneous group CNN for image super-resolution](https://mlsanity.com/paper/2209.12406/) (2022)
- [Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy](https://mlsanity.com/paper/2303.09190/) (2023)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.16776/) (2022)
- [Image Super-resolution with An Enhanced Group Convolutional Neural Network](https://mlsanity.com/paper/2205.14548/) (2022)
- [Compressing Deep Image Super-resolution Models](https://mlsanity.com/paper/2401.00523/) (2023)
- [Lightweight Stepless Super-Resolution of Remote Sensing Images via Saliency-Aware Dynamic Routing Strategy](https://mlsanity.com/paper/2210.07598/) (2022)

## Abstract (arXiv)

Deep convolutional neural networks demonstrate impressive results in the super-resolution domain. A series of studies concentrate on improving peak signal noise ratio (PSNR) by using much deeper layers, which are not friendly to constrained resources. Pursuing a trade-off between the restoration capacity and the simplicity of models is still non-trivial. Recent contributions are struggling to manually maximize this balance, while our work achieves the same goal automatically with neural architecture search. Specifically, we handle super-resolution with a multi-objective approach. We also propose an elastic search tactic at both micro and macro level, based on a hybrid controller that profits from evolutionary computation and reinforcement learning. Quantitative experiments help us to draw a conclusion that our generated models dominate most of the state-of-the-art methods with respect to the individual FLOPS.