Open AccessPosted Content
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
TLDR
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.read more
Citations
More filters
Book ChapterDOI
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
TL;DR: BiSeNet as discussed by the authors designs a spatial path with a small stride to preserve the spatial information and generate high-resolution features, while a context path with fast downsampling strategy is employed to obtain sufficient receptive field.
Journal ArticleDOI
ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation
TL;DR: A deep architecture that is able to run in real time while providing accurate semantic segmentation, and a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy is proposed.
Proceedings ArticleDOI
LinkNet: Exploiting encoder representations for efficient semantic segmentation
TL;DR: In this paper, the authors proposed a novel deep neural network architecture which allows it to learn without any significant increase in number of parameters and achieves state-of-the-art performance on CamVid and Cityscapes dataset.
Posted Content
A Review on Deep Learning Techniques Applied to Semantic Segmentation.
Alberto Garcia-Garcia,Sergio Orts-Escolano,Sergiu Oprea,Victor Villena-Martinez,Jose Garcia-Rodriguez +4 more
TL;DR: A review on deep learning methods for semantic segmentation applied to various application areas as well as mandatory background concepts to help researchers decide which are the ones that best suit their needs and their targets.
Posted Content
An Analysis of Deep Neural Network Models for Practical Applications
TL;DR: This work presents a comprehensive analysis of important metrics in practical applications: accuracy, memory footprint, parameters, operations count, inference time and power consumption and believes it provides a compelling set of information that helps design and engineer efficient DNNs.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.