HCNet: Hierarchical Context Network for Semantic Segmentation

HCNet: Hierarchical Context Network for Semantic Segmentation

Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging to different classes usually have weak feature correlation....

Full description

Bibliographic Details
Main Authors: Yanwen Chong, Congchong Nie, Yulong Tao, Xiaoshu Chen, Shaoming Pan
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Semantic segmentation
self-attention
global context
pixel context
region context
Online Access:https://ieeexplore.ieee.org/document/9210523/

Internet

https://ieeexplore.ieee.org/document/9210523/

Similar Items