Nested attention network based on category contexts learning for semantic segmentation

Abstract The attention mechanism is widely used in the field of semantic segmentation, due to the fact that it can be used to obtain effective long-distance dependencies by assigning different weights to objects according to different tasks. We propose a novel Nested Attention Network (NANet) for se...

Full description

Bibliographic Details

Published in:	Complex & Intelligent Systems
Main Authors:	Tianping Li, Meilin Liu, Dongmei Wei
Format:	Article
Language:	English
Published:	Springer 2024-06-01
Subjects:	Semantic segmentation Attention mechanism Context Lightweight
Online Access:	https://doi.org/10.1007/s40747-024-01520-1