A Gradual Adversarial Training Method for Semantic Segmentation

Deep neural networks (DNNs) have achieved great success in various computer vision tasks. However, they are susceptible to artificially designed adversarial perturbations, which limit their deployment in security-critical applications. In this paper, we propose a gradual adversarial training (GAT) m...

Full description

Bibliographic Details

Published in:	Remote Sensing
Main Authors:	Yinkai Zan, Pingping Lu, Tingyu Meng
Format:	Article
Language:	English
Published:	MDPI AG 2024-11-01
Subjects:	adversarial examples adversarial training deep neural network
Online Access:	https://www.mdpi.com/2072-4292/16/22/4277