Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks
Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge devices. To improve efficiency, some existing approaches parallelize DNN inference across multiple edge devices. How-ever, these techniques introduce significant communication …