Leveraging Transprecision Computing for Machine Vision Applications at the Edge
This work addresses efficiency problems for edge computing applications, but it is incremental as it builds on existing transprecision and optimization techniques.
The paper tackles the challenge of executing multiple machine vision tasks on resource-constrained edge devices by presenting a lightweight approach that dynamically adapts runtime configurations to optimize accuracy, energy, and memory, achieving a 1.6x higher frame processing rate with only a 1% accuracy drop.
Machine vision tasks present challenges for resource constrained edge devices, particularly as they execute multiple tasks with variable workloads. A robust approach that can dynamically adapt in runtime while maintaining the maximum quality of service (QoS) within resource constraints, is needed. The paper presents a lightweight approach that monitors the runtime workload constraint and leverages accuracy-throughput trade-off. Optimisation techniques are included which find the configurations for each task for optimal accuracy, energy and memory and manages transparent switching between configurations. For an accuracy drop of 1%, we show a 1.6x higher achieved frame processing rate with further improvements possible at lower accuracy.