Lightweight semantic segmentation network with configurable context and small object attention

Lightweight semantic segmentation network with configurable context and small object attention

The current semantic segmentation algorithms suffer from encoding feature distortion and small object feature loss. Context information exchange can effectively address the feature distortion problem, but it has the issue of fixed spatial range. Maintaining the input feature resolution can reduce th...

Full description

Bibliographic Details
Main Authors: Chunyu Zhang, Fang Xu, Chengdong Wu, Jinzhao Li
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-10-01
Series:Frontiers in Computational Neuroscience
Subjects:
semantic segmentation
lightweight network
context feature enhancement
small object attention
encoder-decoder
Online Access:https://www.frontiersin.org/articles/10.3389/fncom.2023.1280640/full

Internet

https://www.frontiersin.org/articles/10.3389/fncom.2023.1280640/full

Similar Items