Dense Dual-Path Network for Real-time Semantic Segmentation

by   Xinneng Yang, et al.

Semantic segmentation has achieved remarkable results with high computational cost and a large number of parameters. However, real-world applications require efficient inference speed on embedded devices. Most previous works address the challenge by reducing depth, width and layer capacity of network, which leads to poor performance. In this paper, we introduce a novel Dense Dual-Path Network (DDPNet) for real-time semantic segmentation under resource constraints. We design a light-weight and powerful backbone with dense connectivity to facilitate feature reuse throughout the whole network and the proposed Dual-Path module (DPM) to sufficiently aggregate multi-scale contexts. Meanwhile, a simple and effective framework is built with a skip architecture utilizing the high-resolution feature maps to refine the segmentation output and an upsampling module leveraging context information from the feature maps to refine the heatmaps. The proposed DDPNet shows an obvious advantage in balancing accuracy and speed. Specifically, on Cityscapes test dataset, DDPNet achieves 75.3 single GTX 1080Ti card. Compared with other state-of-the-art methods, DDPNet achieves a significant better accuracy with a comparable speed and fewer parameters.


page 1

page 2

page 3

page 4


Feature Pyramid Encoding Network for Real-time Semantic Segmentation

Although current deep learning methods have achieved impressive results ...

ShuffleSeg: Real-time Semantic Segmentation Network

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

In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images

Recent success of semantic segmentation approaches on demanding road dri...

Context-Integrated and Feature-Refined Network for Lightweight Urban Scene Parsing

Semantic segmentation for lightweight urban scene parsing is a very chal...

ChoiceNet: CNN learning through choice of multiple feature map representations

We introduce a new architecture called ChoiceNet where each layer of the...

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

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

Real-Time Semantic Segmentation via Multiply Spatial Fusion Network

Real-time semantic segmentation plays a significant role in industry app...

Please sign up or login with your details

Forgot password? Click here to reset