CRECA-Net: Class Representation-Enhanced Class-Aware Network for Semantic Segmentation of High-Resolution Remote Sensing Images

High-resolution remote sensing (RS) images exhibit complex backgrounds, large intra-class variability, and low inter-class differences, posing substantial challenges for semantic segmentation. Although existing class-level contextual modeling methods partially alleviate these issues, they often over...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Ruolan Liu, Bingcai Chen, Lin Yu, Shaodong Zhang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2026-03-01
Schriftenreihe:	Remote Sensing
Schlagworte:	class prototype refinement class-level context modeling difficulty-aware loss remote sensing image semantic segmentation
Online-Zugang:	https://www.mdpi.com/2072-4292/18/6/950
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!