论文信息 - Outperformance of Linear-regression-based Methods over Deep Learning in Optical Imaging

Outperformance of Linear-regression-based Methods over Deep Learning in Optical Imaging

Deep learning has been extensively applied in many optical imaging scenarios. But we show linear-regression-based methods may have certain outperformance in two black-box optical imaging problems that were originally solved by deep learning.

Shuming Jiao | Ting Lei | Xiaocong Yuan | Yang Gao | Jun Feng

[1] A. Ozcan,et al. On the use of deep learning for computational imaging , 2019, NanoScience + Engineering.

[2] Wenqi He,et al. Cryptanalysis of random-phase-encoding-based optical cryptosystem via deep learning. , 2019, Optics express.

[3] Fei Wang,et al. Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging. , 2019, Optics express.

[4] Nick Allum,et al. Disparities in science literacy , 2018, Science.