Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

AdaptAV: Continuous Adaption of Vision Models for Autonomous Vehicles Using Cloud-based Oracle

Published in VTC 2024, 2024

Deploying vision perception models in autonomous vehicles requires that we prioritize inference speeds, resulting in a model with shallower architectures and lesser model parameters (i.e., more pruned). Such small models do not generalize well, which could result in poor performance when encountered with novel scenarios. We propose a system that overcomes this by continuously retraining the vision models on the cloud with data uploaded by vehicles. We leverage the abundant compute resources, including machine learning accelerators, of the cloud to run a state-of-the-art, highly accurate oracle model that will guide the retraining process of the on-vehicle model. This newly trained model is transmitted to the vehicle over the network and is utilized by the vehicle for perceptions, leading to improved inference accuracy over time.

Recommended citation: Zhu, Yuheng, et al. "AdaptAV: Continuous Adaption of Vision Models for Autonomous Vehicles Using Cloud-based Oracle." 2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall). IEEE, 2024.
Download Paper

Teaching Assistant

Undergraduate Course, NCSU, CSC, 2023

Teaching Assistant of CSC 246 Concepts and Facilities of Operating Systems for Computer Scientists

Teaching Assistant

Undergraduate Course, NCSU, CSC, 2024

Teaching Assistant of CSC 495 Special Topics in Computer Science: Self-Driving Cars: Theory and Practice

Teaching Assistant

Undergraduate Course, NCSU, CSC, 2025

Teaching Assistant of CSC 246 Concepts and Facilities of Operating Systems for Computer Scientists