딥페이크 검출을 위한 일반화된 메타러닝 EfficientNet 비전 변환기 모델
KCI
-
Title
- 딥페이크 검출을 위한 일반화된 메타러닝 EfficientNet 비전 변환기 모델
-
Alternative Title
- Generalized Meta-Learning EfficientNet Vision Transformer Model for Deepfake Detection
-
Author(s)
- 최영락; Van-Nhan Tran; 임선자; 박진혁; 이석환; 권기룡
- KIOST Author(s)
- Jin, Hyeok Park(박진혁)
-
Alternative Author(s)
- 박진혁
-
Publication Year
- 2024-06
-
Abstract
- Digitally manipulated images that are realistic-looking but fake, which are known as Deepfake. With the remarkable developments in deep generative models, the accessibility and accuracy of manipulated technologies are increasing, leading to fake videos becoming increasingly difficult to identify. Different facial forgery techniques result in complicated data distributions, but Deepfake detection techniques based on CNN(convolutional neural network) architecture are utilized in the majority of Deepfake detection models as binary classification problems. In this paper, we propose a model, named MEViT, which uses a combination of EfficientNet Vision Transformer with a meta-learning-based technique to improve the generalization of the detection model. Furthermore, we propose a learning process to update the model and introduce pair-discrimination loss and domain adjustment loss to improve detection ability across various domains. We also create various experiments on several Deepfake datasets and compare our proposal with many state-of-the-art works to prove the efficiency of our approach.
-
ISSN
- 1229-7771
-
URI
- https://sciwatch.kiost.ac.kr/handle/2020.kiost/45742
-
DOI
- 10.9717/kmms.2024.27.6.663
-
Bibliographic Citation
- 멀티미디어학회논문지, v.27, no.6, pp.663 - 674, 2024
-
Publisher
- 한국멀티미디어학회
-
Keywords
- Deepfake Detection; Vision Transformer; Generalization; Video Forensics; Meta-Learning; EfficientNet
-
Type
- Article
-
Language
- Korean
- Files in This Item:
-
There are no files associated with this item.
Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.