Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
This work addresses the need for efficient super-resolution models for resource-constrained applications, though it is incremental as it builds on existing NAS methods.
The paper tackled the problem of balancing restoration capacity and model simplicity in super-resolution by using neural architecture search to automatically generate models, achieving state-of-the-art performance with respect to FLOPS.
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.