Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection

About

Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. However, these approaches still exhibit the following limitations: (1) Fully fine-tuning ViT-based models from ImageNet weights demands substantial computational and storage resources; (2) ViT-based methods struggle to capture local forgery clues, leading to model bias; (3) These methods limit their scope on only one or few face forgery features, resulting in limited generalizability. To tackle these challenges, this work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach. MoE-FFD only updates lightweight Low-Rank Adaptation (LoRA) and Adapter layers while keeping the ViT backbone frozen, thereby achieving parameter-efficient training. Moreover, MoE-FFD leverages the expressivity of transformers and local priors of CNNs to simultaneously extract global and local forgery clues. Additionally, novel MoE modules are designed to scale the model's capacity and smartly select optimal forgery experts, further enhancing forgery detection performance. Our proposed learning scheme can be seamlessly adapted to various transformer backbones in a plug-and-play manner. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art face forgery detection performance with significantly reduced parameter overhead. The code is released at: https://github.com/LoveSiameseCat/MoE-FFD.

Chenqi Kong, Anwei Luo, Peijun Bao, Yi Yu, Haoliang Li, Zengwei Zheng, Shiqi Wang, Alex C. Kot• 2024

Related benchmarks

TaskDatasetResultRank
Face Forgery DetectionCDF v2
Video AUC0.913
11
Face Forgery DetectionDFDCP
Video-level AUC0.85
8
Showing 2 of 2 rows

Other info

Follow for update