# Hierarchical Neural Architecture Search for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/2003.04619 · HTML: https://mlsanity.com/paper/2003.04619/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2020.

## Built on by (most cited first, 18 of 18)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://mlsanity.com/paper/2207.11938/) (2022)
- [Contrastive Neural Architecture Search with Neural Architecture Comparators](https://mlsanity.com/paper/2103.05471/) (2021)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2101.06658/) (2021)
- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [Multi-scale Attentive Image De-raining Networks via Neural Architecture Search](https://mlsanity.com/paper/2207.00728/) (2022)
- [Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images](https://mlsanity.com/paper/2211.10643/) (2022)
- [Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution](https://mlsanity.com/paper/2105.03939/) (2021)
- [Boosting Semi-Supervised Learning with Contrastive Complementary Labeling](https://mlsanity.com/paper/2212.06643/) (2022)
- [Local-Selective Feature Distillation for Single Image Super-Resolution](https://mlsanity.com/paper/2111.10988/) (2021)
- [Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation](https://mlsanity.com/paper/2509.05746/) (2025)
- [Adaptive Cross-Layer Attention for Image Restoration](https://mlsanity.com/paper/2203.03619/) (2022)
- [Searching Efficient Model-guided Deep Network for Image Denoising](https://mlsanity.com/paper/2104.02525/) (2021)
- [Efficient Image Super-Resolution via Symmetric Visual Attention Network](https://mlsanity.com/paper/2401.08913/) (2024)
- [TND-NAS: Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework](https://mlsanity.com/paper/2111.03892/) (2021)

## Abstract (arXiv)

Deep neural networks have exhibited promising performance in image super-resolution (SR). Most SR models follow a hierarchical architecture that contains both the cell-level design of computational blocks and the network-level design of the positions of upsampling blocks. However, designing SR models heavily relies on human expertise and is very labor-intensive. More critically, these SR models often contain a huge number of parameters and may not meet the requirements of computation resources in real-world applications. To address the above issues, we propose a Hierarchical Neural Architecture Search (HNAS) method to automatically design promising architectures with different requirements of computation cost. To this end, we design a hierarchical SR search space and propose a hierarchical controller for architecture search. Such a hierarchical controller is able to simultaneously find promising cell-level blocks and network-level positions of upsampling layers. Moreover, to design compact architectures with promising performance, we build a joint reward by considering both the performance and computation cost to guide the search process. Extensive experiments on five benchmark datasets demonstrate the superiority of our method over existing methods.