Skip to content

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • Jiansheng Dong
  • Jingling Yuan
  • Lin Li
  • Xian Zhong
  • Weiru Liu
Original languageEnglish
Title of host publication31st International Conference on Tools with Artificial Intelligence (ICTAI2019)
Publisher or commissioning bodyInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
DateAccepted/In press - 27 Aug 2019
Event International Conference on Tools with Artificial Intelligence - Portland, United States
Duration: 4 Nov 20196 Nov 2019
Conference number: 31


Conference International Conference on Tools with Artificial Intelligence
Abbreviated titleICTAI2019
CountryUnited States
Internet address


—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 highresolution features. Compared with other state-of-the-art realtime 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.

    Research areas

  • semantic segmentation, real-time, embedded


International Conference on Tools with Artificial Intelligence

Abbreviated titleICTAI2019
Conference number31
Duration4 Nov 20196 Nov 2019
CountryUnited States
Web address (URL)
Degree of recognitionInternational event

Event: Conference



  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at [insert hyperlink] . Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 1.27 MB, PDF document

    Embargo ends: 1/01/99

    Request copy

View research connections

Related faculties, schools or groups