MIPANet: optimizing RGB-D semantic segmentation through multi-modal interaction and pooling attention

The semantic segmentation of RGB-D images involves understanding objects appearances and spatial relationships within a scene, which necessitates careful consideration of multiple factors. In indoor scenes, the presence of diverse and disorderly objects, coupled with illumination variations and the...

Full description

Bibliographic Details

Published in:	Frontiers in Physics
Main Authors:	Shuai Zhang, Minghong Xie
Format:	Article
Language:	English
Published:	Frontiers Media S.A. 2024-05-01
Subjects:	RGB-D semantic segmentation attention mechanism feature fusion multi-modal interaction feature enhancement
Online Access:	https://www.frontiersin.org/articles/10.3389/fphy.2024.1411559/full