ClassHyPer: ClassMix-Based Hybrid Perturbations for Deep Semi-Supervised Semantic Segmentation of Remote Sensing Imagery

Inspired by the tremendous success of deep learning (DL) and the increased availability of remote sensing data, DL-based image semantic segmentation has attracted growing interest in the remote sensing community. The ideal scenario of DL application requires a vast number of annotation data with the...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Yongjun He, Jinfei Wang, Chunhua Liao, Bo Shan, Xin Zhou
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2022-02-01
Schriftenreihe:	Remote Sensing
Schlagworte:	deep learning remote sensing semantic segmentation transfer learning semi-supervised learning consistency regularization hybrid perturbation
Online-Zugang:	https://www.mdpi.com/2072-4292/14/4/879
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!