In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design prototyping is coupled with machine-driven design exploration to create networks with customized module-level macroarchitecture and microarchitecture designs tailored for the task. Experimental results showed that EdgeSegNet can achieve semantic segmentation accuracy comparable with much larger and computationally complex networks (>20x} smaller model size than RefineNet) as well as achieving an inference speed of ~38.5 FPS on an NVidia Jetson AGX Xavier. As such, the proposed EdgeSegNet is well-suited for low-power edge scenarios.
@article{arxiv.1905.04222,
title = {EdgeSegNet: A Compact Network for Semantic Segmentation},
author = {Zhong Qiu Lin and Brendan Chwyl and Alexander Wong},
journal= {arXiv preprint arXiv:1905.04222},
year = {2019}
}