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

Abstract

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.

arXiv commentAccepted to ICPR20

References in corpus (5)

• Neural Architecture Search with Reinforcement Learning
• MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
• Lightweight Image Super-Resolution with Adaptive Weighted Learning Network
• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
• Improved Crowding Distance for NSGA-II

Cited by in corpus (18)

• AutoML: A Survey of the State-of-the-Art
• A Survey on Evolutionary Neural Architecture Search
• Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
• A Comprehensive Survey on Hardware-Aware Neural Architecture Search
• s-LWSR: Super Lightweight Super-Resolution Network
• 3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
• Multi-Attention Based Ultra Lightweight Image Super-Resolution
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
• A Matrix-in-matrix Neural Network for Image Super Resolution
• NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
• Hierarchical Residual Attention Network for Single Image Super-Resolution
• Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
• On a Sparse Shortcut Topology of Artificial Neural Networks
• Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS
• Memory-Efficient Hierarchical Neural Architecture Search for Image Restoration
• Searching Efficient Model-guided Deep Network for Image Denoising