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

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution BSD100 - 2x upscaling FALSR-A PSNR 32.12 # 16
Image Super-Resolution Set14 - 2x upscaling FALSR-A PSNR 33.55 # 17
Image Super-Resolution Set5 - 2x upscaling FALSR-A PSNR 37.82 # 19
Image Super-Resolution Urban100 - 2x upscaling FALSR-A PSNR 31.93 # 18