Paper
30 November 2022 Improve the speed of semantic segmentation models from multiple perspectives
Yiheng Liang
Author Affiliations +
Proceedings Volume 12456, International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022); 124561Q (2022) https://doi.org/10.1117/12.2659663
Event: International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022), 2022, Qingdao, China
Abstract
The semantic segmentation model needs to output a category for each pixel, which is an intensive prediction task, so it needs more time. Real-world scenarios, such as autopilot, require fast reasoning speeds. Previous work has been to speed up model reasoning in one way or another, so the speed increase is limited. In this paper, we combine multi-level methods to speed up reasoning in a network and obtain remarkable results.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yiheng Liang "Improve the speed of semantic segmentation models from multiple perspectives", Proc. SPIE 12456, International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022), 124561Q (30 November 2022); https://doi.org/10.1117/12.2659663
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Convolution

Computer vision technology

Machine vision

Image processing

Image processing algorithms and systems

Network architectures

RELATED CONTENT


Back to Top