Enhancing the robustness of vision transformer defense against adversarial attacks based on squeeze-and-excitation module

Vision Transformer (ViT) models have achieved good results in computer vision tasks, their performance has been shown to exceed that of convolutional neural networks (CNNs). However, the robustness of the ViT model has been less studied recently. To address this problem, we investigate the robustnes...

Descripció completa

Dades bibliogràfiques

Autors principals:	YouKang Chang, Hong Zhao, Weijie Wang
Format:	Artigo
Idioma:	Inglês
Publicat:	PeerJ Inc. 2023-01-01
Col·lecció:	PeerJ Computer Science
Matèries:	Adversarial attack Defence against adversarial examples Vision transformer SE module
Accés en línia:	https://peerj.com/articles/cs-1197.pdf
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!