AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge
This addresses the deployment dilemma for edge object detection applications, offering a tool for developers, though it appears incremental as it builds on existing methods like pruning and configuration optimization.
The paper tackles the challenge of achieving high accuracy, power efficiency, and real-time performance for object detection on edge devices by proposing AyE-Edge, an automated deployment space search tool. It demonstrates effectiveness with a 96.7% reduction in power consumption compared to SOTA competitors.
Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the deployment dilemma of simultaneously achieving high accuracy, excellent power efficiency, and meeting strict real-time requirements. To tackle this dilemma, we propose AyE-Edge, the first-of-this-kind development tool that explores automated algorithm-device deployment space search to realize Accurate yet power-Efficient real-time object detection on the Edge. Through a collaborative exploration of keyframe selection, CPU-GPU configuration, and DNN pruning strategy, AyE-Edge excels in extensive real-world experiments conducted on a mobile device. The results consistently demonstrate AyE-Edge's effectiveness, realizing outstanding real-time performance, detection accuracy, and notably, a remarkable 96.7% reduction in power consumption, compared to state-of-the-art (SOTA) competitors.