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

7 Jun 2016  ·  Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello ·

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$\times$ faster, requires 75$\times$ less FLOPs, has 79$\times$ 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. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Real-Time Semantic Segmentation Cityscapes test ENet mIoU 58.3% # 31
Time (ms) 13 # 6
Frame (fps) 76.9 # 7
Semantic Segmentation Cityscapes test ENet Mean IoU (class) 58.3% # 90

Methods