An Efficient Semantic Segmentation Method using Pyramid ShuffleNet V2 with Vortex Pooling

Jiansheng Dong, Jingling Yuan, Lin Li, Xian Zhong, Weiru Liu

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

19 Downloads (Pure)

Abstract

Efficient and accurate semantic segmentation is particularly important especially for applications like autonomous driving which requires real-time inference speed and high performance. Many works try to compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. As a result, real-time segmentation task for embedded devices is still an open problem. In this paper, we focus on building a network with better performance possible while still achieve real-time inference speed. We first use a pyramid kernel size to capture more spatial information instead of using just a 3×3 kernel size for DWConvolution in ShuffleNet v2. Meanwhile, an efficient Vortex Pooling module is employed to aggregate the contextual information and generate high-resolution features. Compared with other state-of-the-art real-time semantic segmentation networks, the proposed network achieves similar inference speed and better performance on embedded device. Specifically, we achieve state-of-the-art 73.46% mean IoU on Cityscapes test dataset, for a 768×1024 input, a speed of 46.1 frames per second on NVIDIA Jetson AGX Xavier embedded development board is achieved.
Original languageEnglish
Title of host publication31st International Conference on Tools with Artificial Intelligence (ICTAI2019)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
DOIs
Publication statusPublished - 13 Feb 2020
Event International Conference on Tools with Artificial Intelligence - Portland, United States
Duration: 4 Nov 20196 Nov 2019
Conference number: 31
http://www.ictai2019.org/

Conference

Conference International Conference on Tools with Artificial Intelligence
Abbreviated titleICTAI2019
CountryUnited States
CityPortland
Period4/11/196/11/19
Internet address

Keywords

  • semantic segmentation
  • real-time
  • embedded

Fingerprint Dive into the research topics of 'An Efficient Semantic Segmentation Method using Pyramid ShuffleNet V2 with Vortex Pooling'. Together they form a unique fingerprint.

Cite this