State-of-the-art neural network architectures such as ResNet, MobileNet, and DenseNet have achieved outstanding accuracy over low MACs and small model size counterparts. However, these metrics might not be accurate for predicting the inference time. We suggest that memory traffic for accessing intermediate feature maps can be a factor dominating the inference latency, especially in such tasks as real-time object detection and semantic segmentation of high-resolution video. We propose a Harmonic Densely Connected Network to achieve high efficiency in terms of both low MACs and memory traffic. The new network achieves 35%, 36%, 30%, 32%, and 45% inference time reduction compared with FC-DenseNet-103, DenseNet-264, ResNet-50, ResNet-152, and SSD-VGG, respectively. We use tools including Nvidia profiler and ARM Scale-Sim to measure the memory traffic and verify that the inference latency is indeed proportional to the memory traffic consumption and the proposed network consumes low memory traffic. We conclude that one should take memory traffic into consideration when designing neural network architectures for high-resolution applications at the edge.

No abstract

No abstract

We give a tutorial on video coding principles and standards with emphasis on the latest technology called H.264 or MPEG-4 Part 10. We describe a basic method called block-based hybrid coding employed by most video coding standards. We use graphical illustration to show the functionality. This paper is suitable for those who are interested in implementing video codec in embedded software, pure hardwired, or a combination of both.

We give a tutorial on video coding principles and standards with emphasis on the latest technology called H.264 or MPEG-4 Part 10. We describe a basic method called block-based hybrid coding employed by most video coding standards. We use graphical illustration to show the functionality. This paper is suitable for those who are interested in implementing video codec in embedded software, pure hardwired, or a combination of both.