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...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	YouKang Chang, Hong Zhao, Weijie Wang
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	PeerJ Inc. 2023-01-01
Σειρά:	PeerJ Computer Science
Θέματα:	Adversarial attack Defence against adversarial examples Vision transformer SE module
Διαθέσιμο Online:	https://peerj.com/articles/cs-1197.pdf
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!