An ensemble of modern computer vision models for deepfake detection
This article explores the potential use of modern computer vision architectures for the task of deepfake detection. The following architectures are considered: EfficientNet, Vision Transformer (ViT), VisionLSTM (ViL), Vision KAN, and Mamba Vision. The novelty of the approach lies in the application...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Joint Stock Company "Experimental Scientific and Production Association SPELS
2024-11-01
|
| Series: | Безопасность информационных технологий |
| Subjects: | |
| Online Access: | https://bit.spels.ru/index.php/bit/article/view/1720 |