Photonic Accelerators for Image Segmentation in Autonomous Driving and Defect Detection

TL;DR

This paper explores the use of photonic accelerators for image segmentation in autonomous driving and defect detection, analyzing model suitability, performance, and energy efficiency to advance high-speed, low-power computer vision applications.

Contribution

It identifies segmentation models compatible with photonic accelerators and evaluates their throughput and energy efficiency, highlighting robustness and optimization strategies.

Findings

Certain segmentation models maintain accuracy on photonic accelerators

Photonic accelerators offer high throughput and low energy consumption

Trade-offs exist between model complexity and performance

Abstract

Photonic computing promises faster and more energy-efficient deep neural network (DNN) inference than traditional digital hardware. Advances in photonic computing can have profound impacts on applications such as autonomous driving and defect detection that depend on fast, accurate and energy efficient execution of image segmentation models. In this paper, we investigate image segmentation on photonic accelerators to explore: a) the types of image segmentation DNN architectures that are best suited for photonic accelerators, and b) the throughput and energy efficiency of executing the different image segmentation models on photonic accelerators, along with the trade-offs involved therein. Specifically, we demonstrate that certain segmentation models exhibit negligible loss in accuracy (compared to digital float32 models) when executed on photonic accelerators, and explore the empirical reasoning for their robustness. We also discuss techniques for recovering accuracy in the case of models that do not perform well. Further, we compare throughput (inferences-per-second) and energy consumption estimates for different image segmentation workloads on photonic accelerators. We discuss the challenges and potential optimizations that can help improve the application of photonic accelerators to such computer vision tasks.