- Abstract: The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in practical 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 18x faster, requires 75x less FLOPs, has 79x 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.
- Keywords: Deep learning
- Conflicts: mimuw.edu.pl, purdue.edu, hanyang.ac.kr, iitg.ac.in