GnetSeg: Semantic Segmentation Model Optimized on a 224mW CNN Accelerator Chip at the Speed of 318FPS

TL;DR

GnetSeg is a highly efficient semantic segmentation model optimized for low-power CNN accelerator chips, achieving 318FPS at 224mW with minimal CPU load and novel integer encoding for faster data transfer.

Contribution

The paper introduces GnetSeg, a semantic segmentation model optimized for CNN accelerators, reducing CPU load and employing integer encoding to enhance inference speed and efficiency.

Findings

Achieves 318FPS on a 224mW CNN chip

Maintains high accuracy in person segmentation

Reduces CPU load to zero during inference

Abstract

Semantic segmentation is the task to cluster pixels on an image belonging to the same class. It is widely used in the real-world applications including autonomous driving, medical imaging analysis, industrial inspection, smartphone camera for person segmentation and so on. Accelerating the semantic segmentation models on the mobile and edge devices are practical needs for the industry. Recent years have witnessed the wide availability of CNN (Convolutional Neural Networks) accelerators. They have the advantages on power efficiency, inference speed, which are ideal for accelerating the semantic segmentation models on the edge devices. However, the CNN accelerator chips also have the limitations on flexibility and memory. In addition, the CPU load is very critical because the CNN accelerator chip works as a co-processor with a host CPU. In this paper, we optimize the semantic segmentation model in order to fully utilize the limited memory and the supported operators on the CNN accelerator chips, and at the same time reduce the CPU load of the CNN model to zero. The resulting model is called GnetSeg. Furthermore, we propose the integer encoding for the mask of the GnetSeg model, which minimizes the latency of data transfer between the CNN accelerator and the host CPU. The experimental result shows that the model running on the 224mW chip achieves the speed of 318FPS with excellent accuracy for applications such as person segmentation.