Rethinking fast adversarial training: a splitting technique to overcome catastrophic overfitting

Masoumeh Zareappor, Pourya Shamsolmoali^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Original language	English
Title of host publication	Computer Vision – ECCV 2024 18th European Conference: proceedings
Publisher	Springer Cham
Publication status	Accepted - 01 Jul 2024
Event	European Conference on Computer Vision 2024 - Milan, Italy Duration: 29 Sept 2024 → 04 Oct 2024

Name	Computer Vision – ECCV Proceedings
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference	European Conference on Computer Vision 2024
Abbreviated title	ECCV 2024
Country/Territory	Italy
City	Milan
Period	29/09/2024 → 04/10/2024

Cite this

@inproceedings{1a6af40586c64e5fa7b72b2fabefbef5,

title = "Rethinking fast adversarial training: a splitting technique to overcome catastrophic overfitting",

author = "Masoumeh Zareappor and Pourya Shamsolmoali",

year = "2024",

month = jul,

day = "1",

language = "English",

series = "Computer Vision – ECCV Proceedings",

publisher = "Springer Cham",

booktitle = "Computer Vision – ECCV 2024 18th European Conference: proceedings",

note = "European Conference on Computer Vision 2024, ECCV 2024 ; Conference date: 29-09-2024 Through 04-10-2024",

}

TY - GEN

T1 - Rethinking fast adversarial training: a splitting technique to overcome catastrophic overfitting

AU - Zareappor, Masoumeh

AU - Shamsolmoali, Pourya

PY - 2024/7/1

Y1 - 2024/7/1

M3 - Conference contribution

T3 - Computer Vision – ECCV Proceedings

BT - Computer Vision – ECCV 2024 18th European Conference: proceedings

PB - Springer Cham

T2 - European Conference on Computer Vision 2024

Y2 - 29 September 2024 through 4 October 2024

ER -