Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2024

Abstract

Object detection is a crucial building block for Advanced Driving Assistance Systems (ADAS). These systems require real-time accurate detection on resource-constrained edge devices. Deep learning models are emerging as popular techniques over traditional methods with superior performance. A hurdle in deploying these models is the inference time and computational cost of these models, in addition to training challenges for specialized tasks.We address this using supernet training-based neural architecture search (NAS) to obtain a variety of object detection models at a scale specific to the ADAS application. To this end, we consider a convolutional neural network-based object detection model. We produce a palette of CNN models using the CityScapes, and BDD10K datasets, catering to diverse parameters and accuracy tradeoffs. Our resulting models range between 1.8M to 2.6M parameters with an mAP score within in 29.7% to 33.60% on the CityScapes dataset, and 20.08% to 23.35% on BDD10K. Inspired by the popularity of Large Vision Models, we further develop costeffective transformer-based ADAS Object Detection models. We obtain a palette of transformer models ranging from 69.1M to 113M parameters with mAP score within 28.58% and 32.43% on CityS

Keywords

ADAS, object detection, supernet training, weight-sharing NAS

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 2024 IEEE Conference on Artificial Intelligence (CAI), Singapore, June 25-27

First Page

1005

Last Page

1010

ISBN

9798350354096

Identifier

10.1109/CAI59869.2024.00183

Publisher

IEEE

City or Country

Piscataway, NJ

Additional URL

https://doi.org/10.1109/CAI59869.2024.00183

Download

Share

COinS