Pre-training diffractive optical networks on millions of simple images followed by fine-tuning enables all-optical denoising that raises PSNR from below 8 dB to above 18 dB across diverse datasets including MNIST, ChestMNIST, CIFAR-10 and CelebA.
Advances in neural information processing systems 33, 3833–3845 (2020)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SpectralTrain is a universal training framework that combines curriculum learning and PCA spectral downsampling to deliver 2-7x faster training for hyperspectral image classification across multiple backbones and datasets with only small accuracy trade-offs.
citing papers explorer
-
Pre-training Enables Extraordinary All-optical Image Denoising
Pre-training diffractive optical networks on millions of simple images followed by fine-tuning enables all-optical denoising that raises PSNR from below 8 dB to above 18 dB across diverse datasets including MNIST, ChestMNIST, CIFAR-10 and CelebA.
-
SpectralTrain: A Universal Framework for Hyperspectral Image Classification
SpectralTrain is a universal training framework that combines curriculum learning and PCA spectral downsampling to deliver 2-7x faster training for hyperspectral image classification across multiple backbones and datasets with only small accuracy trade-offs.