Presentation
13 March 2024 Time-lapse image classification boosts diffractive optical network inference accuracy
Author Affiliations +
Proceedings Volume PC12903, AI and Optical Data Sciences V; PC129030A (2024) https://doi.org/10.1117/12.3001804
Event: SPIE OPTO, 2024, San Francisco, California, United States
Abstract
We enhance the accuracy of a diffractive optical network through time-lapse-based inference, which exploits the information diversity obtained by introducing controlled or random displacements between the object and the diffractive network, relative to each other. The numerical blind testing accuracy achieved using this time-lapse-based inference scheme on CIFAR-10 images reached >62%, representing the highest accuracy achieved so far on this dataset using a single diffractive network. Beyond image classification, this framework could also open doors to broader utilization of diffractive networks in tasks involving all-optical spatiotemporal information processing, paving the way for advanced visual computing paradigms.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Md Sadman Sakib Rahman and Aydogan Ozcan "Time-lapse image classification boosts diffractive optical network inference accuracy", Proc. SPIE PC12903, AI and Optical Data Sciences V, PC129030A (13 March 2024); https://doi.org/10.1117/12.3001804
Advertisement
Advertisement
KEYWORDS
Optical networks

Image classification

Data processing

Neural networks

Geometrical optics

Image sensors

Information fusion

Back to Top