DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics

arXiv:2403.14353v1 Announce Type: cross
Abstract: Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots. However, real-world deployment faces challenges due to their limited computational resources and battery power. To tackle these challenges, continuous learning exploits a lightweight "student" model at deployment (inference), leverages a larger "teacher" model for labeling sampled data (labeling), and continuously retrains the student model to adapt to changing scenarios (retraining). This paper highlights …

abstract aerial analytics arxiv autonomous autonomous systems battery challenges computational continuous cs.ar cs.lg cs.ro deep neural network deployment dnn driving exploits however network neural network power resources robots security self-driving self-driving vehicles systems type unmanned aerial vehicles vehicles video video analytics world