Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems

TL;DR

This paper explores methods to accelerate deep neural networks for real-time scene understanding in automotive cyber-physical systems, focusing on weight sharing techniques to achieve significant speedups with minimal accuracy loss.

Contribution

It investigates best practices for applying weight sharing and optimization techniques to accelerate DNNs in automotive perception tasks.

Findings

Significant acceleration of DNNs achieved

Negligible accuracy loss after optimization

Detailed analysis of error types post-optimization

Abstract

Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex and dynamic scenes from visual data. The prediction horizons for those perception systems are very short and inference must often be performed in real time, stressing the need of transforming the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Our goal in this work is to investigate best practices for appropriately applying novel weight sharing techniques, optimizing the available variables and the training procedures towards the significant acceleration of widely adopted DNNs. Extensive evaluation studies carried out using various state-of-the-art DNN models in object detection and tracking experiments, provide details about the type of errors that manifest after the application of weight sharing techniques, resulting in significant acceleration gains with negligible accuracy losses.