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.
@article{arxiv.1901.07261,
title = {Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search},
author = {Xiangxiang Chu and Bo Zhang and Hailong Ma and Ruijun Xu and Qingyuan Li},
journal= {arXiv preprint arXiv:1901.07261},
year = {2020}
}