Improving Model Robustness With Frequency Component Modification and Mixing

Deep neural networks are sensitive to distribution shifts, such as common corruption and adversarial examples, which occur across various frequency spectra. Numerous studies have been conducted to improve model robustness in the frequency domain. However, research that simultaneously addresses safet...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Hyunha Hwang, Se-Hun Kim, Kyujoong Lee, Hyuk-Jae Lee
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2024-01-01
Serier:	IEEE Access
Fag:	Robustness image augmentation discrete Fourier transforms convolutional neural networks image classification
Online adgang:	https://ieeexplore.ieee.org/document/10776988/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!