A Novel Fully Convolutional Auto-Encoder Based on Dual Clustering and Latent Feature Adversarial Consistency for Hyperspectral Anomaly Detection

A Novel Fully Convolutional Auto-Encoder Based on Dual Clustering and Latent Feature Adversarial Consistency for Hyperspectral Anomaly Detection

With the development of artificial intelligence, the ability to capture the background characteristics of hyperspectral imagery (HSI) has improved, showing promising performance in hyperspectral anomaly detection (HAD) tasks. However, existing methods proposed in recent years still suffer from certa...

Full description

Bibliographic Details
Main Authors: Rui Zhao, Zhiwei Yang, Xiangchao Meng, Feng Shao
Format: Article
Language:English
Published: MDPI AG 2024-02-01
Series:Remote Sensing
Subjects:
hyperspectral imagery
anomaly detection
self-supervised learning
fully convolutional auto-encoder
latent feature adversarial consistency
triplet loss
Online Access:https://www.mdpi.com/2072-4292/16/4/717

Internet

https://www.mdpi.com/2072-4292/16/4/717

Similar Items