DeepAI AI Chat
Log In Sign Up

ShuffleSeg: Real-time Semantic Segmentation Network

by   Mostafa Gamal, et al.
University of Alberta
Cairo University

Real-time semantic segmentation is of significant importance for mobile and robotics related applications. We propose a computationally efficient segmentation network which we term as ShuffleSeg. The proposed architecture is based on grouped convolution and channel shuffling in its encoder for improving the performance. An ablation study of different decoding methods is compared including Skip architecture, UNet, and Dilation Frontend. Interesting insights on the speed and accuracy tradeoff is discussed. It is shown that skip architecture in the decoding method provides the best compromise for the goal of real-time performance, while it provides adequate accuracy by utilizing higher resolution feature maps for a more accurate segmentation. ShuffleSeg is evaluated on CityScapes and compared against the state of the art real-time segmentation networks. It achieves 2x GFLOPs reduction, while it provides on par mean intersection over union of 58.3 runs at 15.7 frames per second on NVIDIA Jetson TX2, which makes it of great potential for real-time applications.


Dense Dual-Path Network for Real-time Semantic Segmentation

Semantic segmentation has achieved remarkable results with high computat...

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

Modern deep learning architectures produce highly accurate results on ma...

RTSeg: Real-time Semantic Segmentation Comparative Study

Semantic segmentation benefits robotics related applications especially ...

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

Real-time semantic segmentation plays an important role in practical app...

TransRUPNet for Improved Out-of-Distribution Generalization in Polyp Segmentation

Out-of-distribution (OOD) generalization is a critical challenge in deep...

A De-raining semantic segmentation network for real-time foreground segmentation

Few researches have been proposed specifically for real-time semantic se...

A novel dual skip connection mechanism in U-Nets for building footprint extraction

The importance of building footprints and their inventory has been recog...

Code Repositories


RTSeg: Real-time Semantic Segmentation Comparative Study

view repo