# Compressed Meta-Optical Encoder for Image Classification

arXiv: https://arxiv.org/abs/2406.06534 · HTML: https://mlsanity.com/paper/2406.06534/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 12 of 12)

- [Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity](https://mlsanity.com/paper/2106.15933/) (2021)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [The physics of optical computing](https://mlsanity.com/paper/2308.00088/) (2023)
- [Image sensing with multilayer, nonlinear optical neural networks](https://mlsanity.com/paper/2207.14293/) (2022)
- [Network Augmentation for Tiny Deep Learning](https://mlsanity.com/paper/2110.08890/) (2021)
- [An Optical Frontend for a Convolutional Neural Network](https://mlsanity.com/paper/1901.03661/) (2018)
- [Meta-optic Accelerators for Object Classifiers](https://mlsanity.com/paper/2201.11034/) (2022)
- [Spatially Varying Nanophotonic Neural Networks](https://mlsanity.com/paper/2308.03407/) (2023)
- [Photonic Advantage of Optical Encoders](https://mlsanity.com/paper/2305.01743/) (2023)
- [Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks](https://mlsanity.com/paper/2102.13323/) (2021)
- [KL-Divergence-Based Region Proposal Network for Object Detection](https://mlsanity.com/paper/2005.11220/) (2020)
- [BI-MAML: Balanced Incremental Approach for Meta Learning](https://mlsanity.com/paper/2006.07412/) (2020)

## Built on by (most cited first, 6 of 6)

- [Towards SAR Automatic Target Recognition MultiCategory SAR Image Classification Based on Light Weight Vision Transformer](https://mlsanity.com/paper/2407.06128/) (2024)
- [Transferable polychromatic optical encoder for neural networks](https://mlsanity.com/paper/2411.02697/) (2024)
- [Neural Tangent Knowledge Distillation for Optical Convolutional Networks](https://mlsanity.com/paper/2508.08421/) (2025)
- [Physical Foundation Models: Fixed hardware implementations of large-scale neural networks](https://mlsanity.com/paper/2604.27911/) (2026)
- [Spatially Parallel All-optical Neural Networks](https://mlsanity.com/paper/2509.23611/) (2025)
- [VLM-Aware Meta-Optic Front-End Design for Frozen Vision-Language Models](https://mlsanity.com/paper/2606.27646/) (2026)

## Abstract (arXiv)

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 at a significant reduction in accuracy. In this work, 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 to 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 86K in the hybrid compressed network enabled by the optical frontend. This constitutes over two orders of magnitude reduction in latency and power consumption. Furthermore, we experimentally demonstrate that the classification accuracy of the system exceeds 93% on the MNIST dataset.