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

07/26/2019
by   Gen Li, et al.
5

As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance. Recently, due to the increasing demand for autonomous systems and robots, it is significant to make a tradeoff between accuracy and inference speed. In this paper, we propose a novel Depthwise Asymmetric Bottleneck (DAB) module to address this dilemma, which efficiently adopts depth-wise asymmetric convolution and dilated convolution to build a bottleneck structure. Based on the DAB module, we design a Depth-wise Asymmetric Bottleneck Network (DABNet) especially for real-time semantic segmentation, which creates sufficient receptive field and densely utilizes the contextual information. Experiments on Cityscapes and CamVid datasets demonstrate that the proposed DABNet achieves a balance between speed and precision. Specifically, without any pretrained model and postprocessing, it achieves 70.1 with only 0.76 million parameters and a speed of 104 FPS on a single GTX 1080Ti card.

READ FULL TEXT

page 1

page 2

page 9

research
03/16/2021

EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation

Due to real-time image semantic segmentation needs on power constrained ...
research
09/17/2018

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

Real-time semantic segmentation plays an important role in practical app...
research
03/22/2021

CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation

Real-time semantic segmentation is playing a more important role in comp...
research
12/12/2018

Concentrated-Comprehensive Convolutions for lightweight semantic segmentation

The semantic segmentation requires a lot of computational cost. The dila...
research
06/24/2019

ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

The recent years have witnessed great advances for semantic segmentation...
research
09/15/2023

Efficient Polyp Segmentation Via Integrity Learning

Accurate polyp delineation in colonoscopy is crucial for assisting in di...
research
02/23/2023

Efficient Context Integration through Factorized Pyramidal Learning for Ultra-Lightweight Semantic Segmentation

Semantic segmentation is a pixel-level prediction task to classify each ...

Please sign up or login with your details

Forgot password? Click here to reset