Transferable polychromatic optical encoder for neural networks

Minho Choi (), Jinlin Xiang, Anna Wirth-Singh, Seung-Hwan Baek, Eli Shlizerman () and Arka Majumdar ()
Additional contact information
Minho Choi: University of Washington
Jinlin Xiang: University of Washington
Anna Wirth-Singh: University of Washington
Seung-Hwan Baek: Pohang University of Science and Technology
Eli Shlizerman: University of Washington
Arka Majumdar: University of Washington

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract Artificial neural networks have fundamentally transformed the field of computer vision, providing unprecedented performance. However, these neural networks for image processing demand substantial computational resources, often hindering real-time operation. In this work, we demonstrate an optical encoder that can perform convolution simultaneously in three color channels during the image capture, effectively implementing several initial convolutional layers of the network. Such an optical encoding results in ~ 24, 000 × reduction in computational operations, with a state-of-the-art classification accuracy (~73.2%) in free-space optical system. In addition, our analog optical encoder, trained for CIFAR-10 data, can be transferred to the ImageNet subset, High-10, without any modifications, and still exhibits moderate accuracy. The proposed method can decrease total system-level energy more than two orders of magnitude per a single object classification. Our results evidence the potential of hybrid optical/digital computer vision system in which the optical frontend can pre-process an ambient scene to reduce the energy and latency of the whole computer vision system.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-61338-4 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-61338-4

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-61338-4

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().