Publication:
EfficientNets for DeepFake Detection: Comparison of Pretrained Models

Простая страница элемента
dc.contributor.authorPokroy, A. A.
dc.contributor.authorEgorov, A. D.
dc.contributor.authorЕгоров, Алексей Дмитриевич
dc.date.accessioned2024-11-29T15:24:01Z
dc.date.available2024-11-29T15:24:01Z
dc.date.issued2021
dc.description.abstract© 2021 IEEE.Rapid advances in media generation techniques have made the creation of AI-generated fake face videos more accessible than ever before. In order to accelerate the development of new ways to expose forged videos, Facebook created Deep Fake Detection Challenge (DFDC), which demonstrated multiple approaches to solve this problem. Analysis of top-performing solutions revealed that all winners used pre-trained EfficientNet networks, which was finetuned on videos containing face manipulations. Because of this observation, we decide to compare the performance of EfficientNets models within the task of detecting fake videos. For comparison, we use models, based on the highest-performing entrant of DFDC, entered by Selim Seferbekov, and the DFDC dataset as training data. Our experiments show that there is no strong correlation between model performance and its size. The best accuracy was achieved by B4 and B5 models.
dc.format.extentС. 598-600
dc.identifier.citationPokroy, A. A. EfficientNets for DeepFake Detection: Comparison of Pretrained Models / Pokroy, A.A., Egorov, A.D. // Proceedings of the 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2021. - 2021. - P. 598-600. - 10.1109/ElConRus51938.2021.9396092
dc.identifier.doi10.1109/ElConRus51938.2021.9396092
dc.identifier.urihttps://www.doi.org/10.1109/ElConRus51938.2021.9396092
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85104792685&origin=resultslist
dc.identifier.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000669709800132
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/23975
dc.relation.ispartofProceedings of the 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2021
dc.titleEfficientNets for DeepFake Detection: Comparison of Pretrained Models
dc.typeConference Paper
dspace.entity.typePublication
relation.isAuthorOfPublicationf8930215-b423-4092-b507-b5a1ad42f6d5
relation.isAuthorOfPublication.latestForDiscoveryf8930215-b423-4092-b507-b5a1ad42f6d5
relation.isOrgUnitOfPublication010157d0-1f75-46b2-ab5b-712e3424b4f5
relation.isOrgUnitOfPublication.latestForDiscovery010157d0-1f75-46b2-ab5b-712e3424b4f5
Файлы
Коллекции
Публикации