Advantages of Broadband Metalenses for Generalizable Image Classification

TL;DR

This paper demonstrates that broadband metalenses can serve as effective, generalizable optical encoders in neural networks, achieving high classification accuracy across various sensors and outperforming traditional optics.

Contribution

It introduces a broadband metalens for ONNs that maintains accuracy across different sensors and digital backends, advancing the design of generalizable optical neural network components.

Findings

Broadband metalenses achieve comparable accuracy to high-end optics.

They outperform hyperboloid baselines across sensor sizes.

Optimization balances modulation transfer function across wavelengths.

Abstract

Optical neural networks (ONNs) are gaining increasing attention to accelerate machine learning tasks. In particular, static meta-optical encoders designed for task-specific pre-processing have demonstrated orders of magnitude smaller energy consumption over purely digital counterparts, albeit at the cost of a slight degradation in classification accuracy. However, a lack of generalizability poses serious challenges for wide deployment of static meta-optical front-ends. Here, we investigate the utility of a single-layer metalens as a meta-optical encoder in ONNs for generalizable image classification. Specifically, we show that a visible-spectrum broadband metalens can achieve image classification accuracy comparable to high-end, sensor-limited optics and consistently outperforms the corresponding hyperboloid baseline across a wide range of sensor pixel sizes and digital backends. We further design an end-to-end optimized single-aperture metasurface for ImageNet classification and observe that the optimization tends to balance the modulation transfer function (MTF) across wavelengths within the sensor-detectable passband. Together, these observations suggest that the preservation of spatial-frequency information is an important factor influencing the performance of ONNs. Our results provide physical insight into the process of task-driven optical optimization and offer practical guidance for the design of high-performance ONNs and meta-optical encoders for generalizable computer vision tasks.