PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search

arXiv:2403.15712v1 Announce Type: new
Abstract: Multiple object tracking is a critical task in autonomous driving. Existing works primarily focus on the heuristic design of neural networks to obtain high accuracy. As tracking accuracy improves, however, neural networks become increasingly complex, posing challenges for their practical application in real driving scenarios due to the high level of latency. In this paper, we explore the use of the neural architecture search (NAS) methods to search for efficient architectures for tracking, aiming for …

abstract accuracy application architecture arxiv autonomous autonomous driving become challenges cs.cv cs.ro design driving focus however modal multi-modal multiple networks neural architecture search neural networks object pareto pnas practical search tracking type