Domain-Adaptive Online Active Learning for Real-Time Intelligent Video Analytics on Edge Devices

Deep Learning (DL) for intelligent video analytics is increasingly pervasive in various application domains, ranging from Healthcare to Industry 5.0. A significant trend involves deploying DL models on edge devices with limited resources. Techniques such as pruning, quantization, and early-exit have demonstrated the feasibility of real-time inference at the edge by compressing and optimizing Deep Neural Networks (DNNs). However, adapting pre-trained models to new and dynamic scenarios remains a significant challenge. While solutions like domain adaptation, active learning, and teacher-student knowl- edge distillation contribute to addressing this challenge, they often rely on cloud or well-equipped computing platforms for fine tuning. In this study, we propose a framework for domain- adaptive online active learning of DNN models tailored for intelligent video analytics on resource-constrained devices. Our framework employs a knowledge distillation approach where both teacher and student models are deployed on the edge device. To determine when to retrain the student DNN model without ground-truth or cloud-based teacher inference, our model utilizes singular value decomposition of input data. It implements the identification of key data frames and efficient retraining of the student through the teacher execution at the edge, aiming to prevent model overfitting. We evaluate the framework through two case studies: human pose estimation and car object detection, both implemented on an NVIDIA Jetson NX device.