Does deep learning always outperform simple linear regression in optical imaging?
arXiv:1911.00353 · doi:10.1364/OE.382319
Abstract
Deep learning has been extensively applied in many optical imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box optical imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.
References in corpus (13)
- Phase recovery and holographic image reconstruction using deep learning in neural networks
- Deep Learning Microscopy
- Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
- Fringe pattern analysis using deep learning
- End-to-end Deep Learning of Optical Fiber Communications
- Intelligent Nanophotonics: Merging Photonics and Artificial Intelligence at the Nanoscale
- Deep learning approach to Fourier ptychographic microscopy
- Experimental comparison of single-pixel imaging algorithms
- Review on Optical Image Hiding and Watermarking Techniques
- Computational ghost imaging using deep learning
- Optical machine learning with incoherent light and a single-pixel detector
- Illumination Pattern Design with Deep Learning for Single-Shot Fourier Ptychographic Microscopy
- Deep Iterative Reconstruction for Phase Retrieval