Enabling Incremental Knowledge Transfer for Object Detection at the Edge
This addresses energy and latency issues for object detection on user-end edge devices, representing an incremental improvement through a hybrid approach.
The paper tackles the high computational cost of deep neural networks for object detection on resource-limited edge devices by proposing a system that uses a shallow neural network for inference and a knowledge transfer mechanism to update it from a powerful edge device, achieving 78% energy savings and 71% faster inference time compared to running a deep model locally.
Object detection using deep neural networks (DNNs) involves a huge amount of computation which impedes its implementation on resource/energy-limited user-end devices. The reason for the success of DNNs is due to having knowledge over all different domains of observed environments. However, we need a limited knowledge of the observed environment at inference time which can be learned using a shallow neural network (SHNN). In this paper, a system-level design is proposed to improve the energy consumption of object detection on the user-end device. An SHNN is deployed on the user-end device to detect objects in the observing environment. Also, a knowledge transfer mechanism is implemented to update the SHNN model using the DNN knowledge when there is a change in the object domain. DNN knowledge can be obtained from a powerful edge device connected to the user-end device through LAN or Wi-Fi. Experiments demonstrate that the energy consumption of the user-end device and the inference time can be improved by 78% and 71% compared with running the deep model on the user-end device.