ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

@article{Mehta2018ESPNetES,
  title={ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation},
  author={Sachin Mehta and Mohammad Rastegari and A. Caspi and L. Shapiro and Hannaneh Hajishirzi},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.06815}
}
We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. [...] Key Result Our network can process high resolution images at a rate of 112 and 9 frames per second on a standard GPU and edge device, respectively.Expand
Efficient Semantic Segmentation Using Spatio-Channel Dilated Convolutions
TLDR
An efficient convolution method, Spatio-Channel dilated convolution (SCDC) which is composed of structured sparse kernels based on the principle of split-transform-merge is introduced, which employs the kernels whose shapes are dilated, not only in spatial domain, but also in channel domain, using a channel sampling approach. Expand
ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
TLDR
This paper designs an efficient symmetric network, called (ESNet), to address the problem of real-time semantic segmentation on CityScapes dataset, and achieves state-of-the-art results in terms of speed and accuracy trade-off. Expand
Real-Time Semantic Segmentation With Fast Attention
TLDR
The proposed architecture relies on the fast spatial attention, which is a simple yet efficient modification of the popular self-attention mechanism and captures the same rich spatial context at a small fraction of the computational cost, by changing the order of operations. Expand
LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
TLDR
A new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) is explored and applied short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model for semantic image segmentation. Expand
Real-Time Semantic Segmentation Network for Edge Deployment
TLDR
This paper proposes MFANet with efficient multi-fiber unit and attention module, which obtains well balance between speed and performance, and is capable of industrial deployment of real-time semantic segmentation network. Expand
Feature Pyramid Encoding Network for Real-time Semantic Segmentation
TLDR
A lightweight feature pyramid encoding network (FPENet) is proposed to make a good trade-off between accuracy and speed and outperforms existing real-time methods with fewer parameters and improved inference speed on the Cityscapes and CamVid benchmark datasets. Expand
Efficient Fast Semantic Segmentation Using Continuous Shuffle Dilated Convolutions
TLDR
An efficient fast semantic segmentation network (EFSNet) that employs a continuous shuffle dilated convolution (CSDC) and a up-sampling module that achieves efficient segmentation with low resource consumption is proposed. Expand
Efficient Joined Pyramid Network Applied to Semantic Segmentation for GPU Embedded System
TLDR
According to the results, EJPNet not only has the best number of parameters, FLOPS, and time processing, but also this network has one of the best precisions and is a feasible semantic segmentation method for embedded systems applications. Expand
EACNet: Enhanced Asymmetric Convolution for Real-Time Semantic Segmentation
TLDR
An enhanced asymmetric convolution network (EACNet) is presented to seek a balance between accuracy and speed to extract short-range and long-range features and applies a bilateral structure in which the detail branch preserves low-level spatial details while the semantic branch captures high-level context information. Expand
Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
TLDR
A novel convolutional network named Efficient Dense modules with Asymmetric convolution (EDANet) is proposed, which employs an asymmetric Convolution structure and incorporates dilated convolution and dense connectivity to achieve high efficiency at low computational cost and model size. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 65 REFERENCES
Understanding Convolution for Semantic Segmentation
TLDR
DUC is designed to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling, and a hybrid dilated convolution (HDC) framework in the encoding phase is proposed. Expand
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
TLDR
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner. Expand
Convolutional feature masking for joint object and stuff segmentation
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
This paper proposes a joint method to handle objects and “stuff” (e.g., grass, sky, water) in the same framework and presents state-of-the-art results on benchmarks of PASCAL VOC and new PASCal-CONTEXT. Expand
Fully Convolutional Networks for Semantic Segmentation
TLDR
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Expand
ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation
TLDR
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. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
TLDR
Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet. Expand
Striving for Simplicity: The All Convolutional Net
TLDR
It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Expand
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
TLDR
An image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address the challenging task of real-time semantic segmentation is proposed and in-depth analysis of the framework is provided. Expand
...
1
2
3
4
5
...