Adversarial Defense Method Based on Latent Representation Guidance for Remote Sensing Image Scene Classification

Adversarial Defense Method Based on Latent Representation Guidance for Remote Sensing Image Scene Classification

Deep neural networks have made great achievements in remote sensing image analyses; however, previous studies have shown that deep neural networks exhibit incredible vulnerability to adversarial examples, which raises concerns about regional safety and production safety. In this paper, we propose an...

Full description

Bibliographic Details
Main Authors: Qingan Da, Guoyin Zhang, Wenshan Wang, Yingnan Zhao, Dan Lu, Sizhao Li, Dapeng Lang
Format: Article
Language:English
Published: MDPI AG 2023-09-01
Series:Entropy
Subjects:
adversarial denoising
self-supervised learning
latent representation
normalized mutual information
cross-entropy
Online Access:https://www.mdpi.com/1099-4300/25/9/1306

Internet

https://www.mdpi.com/1099-4300/25/9/1306

Similar Items