ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation (2016-06-07T00:00:00.000000Z)

TL;DR

A novel deep neural network architecture named ENet (efficient neural network), created specifically for tasks requiring low latency operation, which is up to 18 times faster, requires 75% less FLOPs, has 79% less parameters, and provides similar or better accuracy to existing models.

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$\times$ 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.

Authors

Adam Paszke

3 papers

E. Culurciello

2 papers

Abhishek Chaurasia

1 papers

TL;DR

Abstract

Authors

References35 items

The Cityscapes Dataset for Semantic Urban Scene Understanding

Deep Networks with Stochastic Depth

Identity Mappings in Deep Residual Networks

Deep Residual Learning for Image Recognition

Rethinking the Inception Architecture for Computer Vision

Multi-Scale Context Aggregation by Dilated Convolutions

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

SUN RGB-D: A RGB-D scene understanding benchmark suite

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling

Learning Deconvolution Network for Semantic Segmentation

Conditional Random Fields as Recurrent Neural Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Adam: A Method for Stochastic Optimization

Flattened Convolutional Neural Networks for Feedforward Acceleration

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

Efficient object localization using Convolutional Networks

Fully convolutional networks for semantic segmentation

cuDNN: Efficient Primitives for Deep Learning

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

Learning Hierarchical Features for Scene Labeling

ImageNet classification with deep convolutional neural networks

Segmentation as selective search for object recognition

Multimodal Deep Learning

Large-scale image retrieval with compressed Fisher vectors

Scene Text Recognition using Higher Order Language Priors

Segmentation and Recognition Using Structure from Motion Point Clouds

Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition

Convolutional networks for images, speech, and time series

Combining Appearance and Structure from Motion Features for Road Scene Understanding

TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names