SOTAVerified

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

2016-06-07Code Available1· sign in to hype

Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Efficient Neural NetworkReal-Time Semantic SegmentationSemantic Segmentation

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
Cityscapes testENetMean IoU (class)58.3—Unverified
ScanNetV2ENetMean IoU37.6—Unverified

Reproductions