arXiv (Cornell University) · 2019 · 87 citations · 13 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningOptimizationDeep LearningEvolutionary OptimizationNeural NetworksOptimization For Machine LearningReinforcement LearningArchitecture SearchDeep Reinforcement LearningImage Super-resolutionNeural Architecture SearchOptimization AlgorithmsSignal-to-noise RatioSignal-to-noise Ratio OptimizationSuper-resolution
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.
13
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Image Quality Metrics: PSNR vs. SSIM
Alain Horé, Djemel Ziou · 2010 · 4.4K citations
Residual Dense Network for Image Super-Resolution
Yulun Zhang, Yapeng Tian, Yu Kong et al. · 2018 · 4.1K citations
Neural Architecture Search with Reinforcement Learning
Barret Zoph, Quoc V. Le · arXiv (Cornell University) · 2016 · 3.9K citations · Full text