Toward Enhanced Adversarial Robustness Generalization in Object Detection: Feature Disentangled Domain Adaptation for Adversarial Training

Recent research has shown that deep learning models are likely to make incorrect predictions even when exposed to minor perturbations. To address this, training models on adversarial examples, particularly through Adversarial Training (AT), has gained attraction. However, traditional AT is prone to...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Yoojin Jung, Byung Cheol Song
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2024-01-01
Serija:	IEEE Access
Teme:	Adversarial robustness adversarial training domain adaptation feature disentanglement
Online dostop:	https://ieeexplore.ieee.org/document/10769077/
Oznake:	Označite Brez oznak, prvi označite!