Time-lapse image classification using a diffractive neural network

Abstract

Diffractive deep neural networks (D2NNs) define an all-optical computing framework comprised of spatially engineered passive surfaces that collectively process optical input information by modulating the amplitude and/or the phase of the propagating light. Diffractive optical networks complete their computational tasks at the speed of light propagation through a thin diffractive volume, without any external computing power while exploiting the massive parallelism of optics. Diffractive networks were demonstrated to achieve all-optical classification of objects and perform universal linear transformations. Here we demonstrate, for the first time, a "time-lapse" image classification scheme using a diffractive network, significantly advancing its classification accuracy and generalization performance on complex input objects by using the lateral movements of the input objects and/or the diffractive network, relative to each other. In a different context, such relative movements of the objects and/or the camera are routinely being used for image super-resolution applications; inspired by their success, we designed a time-lapse diffractive network to benefit from the complementary information content created by controlled or random lateral shifts. We numerically explored the design space and performance limits of time-lapse diffractive networks, revealing a blind testing accuracy of 62.03% on the optical classification of objects from the CIFAR-10 dataset. This constitutes the highest inference accuracy achieved so far using a single diffractive network on the CIFAR-10 dataset. Time-lapse diffractive networks will be broadly useful for the spatio-temporal analysis of input signals using all-optical processors.

17 Pages, 4 Figures, 2 Tables

References in corpus (8)

• Misalignment Resilient Diffractive Optical Networks
• Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network
• Diffractive all-optical computing for quantitative phase imaging
• To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
• Super-resolution image display using diffractive decoders
• Polarized deep diffractive neural network for classification, generation, multiplexing and de-multiplexing of orbital angular momentum modes
• Computer-free, all-optical reconstruction of holograms using diffractive networks
• All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces

Cited by in corpus (4)

• Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processors
• Complex-valued universal linear transformations and image encryption using spatially incoherent diffractive networks
• Transferable polychromatic optical encoder for neural networks
• Integration of Programmable Diffraction with Digital Neural Networks