EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Compressed meta-optical encoder for image classification

Anna Wirth-Singh, Jinlin Xiang, Minho Choi, Johannes E. Fröch, Luocheng Huang, Shane Colburn, Eli Shlizerman, Arka Majumdar

Advanced Photonics Nexus · 25.02.2025 · 4 (02) · 1-10

DOI: 10.1117/1.apn.4.2.026009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Photonics Nexus, erschienen am 25.02.2025. Verfasst von Anna Wirth-Singh und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification, and computer-vision tasks. However, implementing optical nonlinearity is challenging, and omitting the nonlinear layers in a standard CNN comes with a significant reduction in accuracy. We use knowledge distillation to compress modified AlexNet to a single linear convolutional layer and an electronic backend (two fully connected layers). We obtain comparable performance with a purely electronic CNN with five convolutional layers and three fully connected layers. We implement the convolution optically via engineering the point spread function of an inverse-designed meta-optic. Using this hybrid approach, we estimate a reduction in multiply-accumulate operations from 17M in a conventional electronic modified AlexNet to only 86 K in the hybrid compressed network enabled by the optical front end. This constitutes over 2 orders of magnitude of reduction in latency and power consumption. Furthermore, we experimentally demonstrate that the classification accuracy of the system exceeds 93% on the MNIST dataset of handwritten digits.

Zitieren

APA

Wirth-Singh, A., Xiang, J., Choi, M., Fröch, J. E., Huang, L., Colburn, S., Shlizerman, E., & Majumdar, A. (2025). Compressed meta-optical encoder for image classification. Advanced Photonics Nexus, 4(02), 1-10. https://doi.org/10.1117/1.apn.4.2.026009

Vancouver

Wirth-Singh A, Xiang J, Choi M, Fröch JE, Huang L, Colburn S, et al. Compressed meta-optical encoder for image classification. Advanced Photonics Nexus. 2025;4(02):1-10. doi:10.1117/1.apn.4.2.026009

BibTeX
@article{WirthSingh2025,
  author = {Wirth-Singh, Anna and Xiang, Jinlin and Choi, Minho and Fröch, Johannes E. and Huang, Luocheng and Colburn, Shane and Shlizerman, Eli and Majumdar, Arka},
  title = {Compressed meta-optical encoder for image classification},
  journal = {Advanced Photonics Nexus},
  year = {2025},
  volume = {4},
  number = {02},
  pages = {1--10},
  doi = {10.1117/1.apn.4.2.026009}
}
Kostenlos starten →