DeepAI AI Chat
Log In Sign Up

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

by   Rudra P K Poudel, et al.

Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since naive adaptation of such systems to reduce computational cost (speed, memory and energy) causes a significant drop in accuracy. We propose ContextNet, a new deep neural network architecture which builds on factorized convolution, network compression and pyramid representations to produce competitive semantic segmentation in real-time with low memory requirements. ContextNet combines a deep branch at low resolution that captures global context information efficiently with a shallow branch that focuses on high-resolution segmentation details. We analyze our network in a thorough ablation study and present results on the Cityscapes dataset, achieving 66.1 accuracy at 18.2 frames per second at full (1024x2048) resolution.


page 2

page 8


CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation

With the increasing demand of autonomous machines, pixel-wise semantic s...

Fast-SCNN: Fast Semantic Segmentation Network

The encoder-decoder framework is state-of-the-art for offline semantic i...

ShuffleSeg: Real-time Semantic Segmentation Network

Real-time semantic segmentation is of significant importance for mobile ...

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

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

PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller

Two-branch network architecture has shown its efficiency and effectivene...

Bi-direction Context Propagation Network for Real-time Semantic Segmentation

Spatial details and context correlations are two types of critical infor...