The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point operations and have long run-times that hinder their usability. In this paper, we propose a novel deep neural network architecture named ENet (efficient neural network), created specifically for tasks requiring low latency operation. ENet is up to 18× faster, requires 75× less FLOPs, has 79× less parameters, and provides similar or better accuracy to existing models. We have tested it on CamVid, Cityscapes and SUN datasets and report on comparisons with existing state-of-the-art methods, and the trade-offs between accuracy and processing time of a network. We present performance measurements of the proposed architecture on embedded systems and suggest possible software improvements that could make ENet even faster.
@article{arxiv.1606.02147,
title = {ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation},
author = {Adam Paszke and Abhishek Chaurasia and Sangpil Kim and Eugenio Culurciello},
journal= {arXiv preprint arXiv:1606.02147},
year = {2016}
}