ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

[guanfuchen]

related paper

摘要

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.

[guanfuchen]

model architecture

detail in table

[guanfuchen]

network design choices

[guanfuchen]

results

[guanfuchen]

conclusion