Self-Supervised Contrastive Learning for Hyperspectral Anomaly Detection With Block-Pseudolabel Masked Data Augmentation

Hyperspectral anomaly detection (HAD) aims to identify targets deviating from normal patterns of background. However, the lack of labeled samples poses significant challenges to the task. Self-supervised deep learning methods have shown promising results in this scenario, but they often fall into pa...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Meiping Song, Zhiyuan Jing, Xudong Sun, Yisha Liu, Haimo Bao, Chunyan Yu
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2026-01-01
Edice:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Témata:	Contrastive learning data augmentation hyperspectral anomaly detection (HAD) patches pseudolabel self-supervised
On-line přístup:	https://ieeexplore.ieee.org/document/11367285/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!