Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation

09/17/2018
by   Shao-Yuan Lo, et al.
4

Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most research working on semantic segmentation focuses on accuracy with little consideration for efficiency. Several existing studies that emphasize high-speed inference often cannot produce high-accuracy segmentation results. In this paper, we propose a novel convolutional network named Efficient Dense modules with Asymmetric convolution (EDANet), which employs an asymmetric convolution structure incorporating the dilated convolution and the dense connectivity to attain high efficiency at low computational cost, inference time, and model size. Compared to FCN, EDANet is 11 times faster and has 196 times fewer parameters, while it achieves a higher the mean of intersection-over-union (mIoU) score without any additional decoder structure, context module, post-processing scheme, and pretrained model. We evaluate EDANet on Cityscapes and CamVid datasets to evaluate its performance and compare it with the other state-of-art systems. Our network can run on resolution 512x1024 inputs at the speed of 108 and 81 frames per second on a single GTX 1080Ti and Titan X, respectively.

READ FULL TEXT

page 7

page 15

page 16

research
07/26/2019

DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation

As a pixel-level prediction task, semantic segmentation needs large comp...
research
03/24/2021

MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation

In recent years, how to strike a good trade-off between accuracy and inf...
research
05/11/2018

ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time

Modern deep learning architectures produce highly accurate results on ma...
research
03/10/2018

ShuffleSeg: Real-time Semantic Segmentation Network

Real-time semantic segmentation is of significant importance for mobile ...
research
10/21/2020

Dense Dual-Path Network for Real-time Semantic Segmentation

Semantic segmentation has achieved remarkable results with high computat...
research
12/03/2019

Real-Time Panoptic Segmentation from Dense Detections

Panoptic segmentation is a complex full scene parsing task requiring sim...
research
06/22/2018

Efficient Semantic Segmentation using Gradual Grouping

Deep CNNs for semantic segmentation have high memory and run time requir...

Please sign up or login with your details

Forgot password? Click here to reset