Hierarchical Deep Fusion Framework for Multi-dimensional Facial Forgery Detection - The 2024 Global Deepfake Image Detection Challenge
This addresses digital security challenges posed by deepfakes, though it is incremental as it combines existing models for a specific task.
The paper tackled the problem of detecting facial forgeries across diverse manipulation techniques by introducing the Hierarchical Deep Fusion Framework (HDFF), an ensemble architecture that integrates four pre-trained models, achieving a score of 0.96852 and ranking 20th out of 184 teams in a competition.
The proliferation of sophisticated deepfake technology poses significant challenges to digital security and authenticity. Detecting these forgeries, especially across a wide spectrum of manipulation techniques, requires robust and generalized models. This paper introduces the Hierarchical Deep Fusion Framework (HDFF), an ensemble-based deep learning architecture designed for high-performance facial forgery detection. Our framework integrates four diverse pre-trained sub-models, Swin-MLP, CoAtNet, EfficientNetV2, and DaViT, which are meticulously fine-tuned through a multi-stage process on the MultiFFDI dataset. By concatenating the feature representations from these specialized models and training a final classifier layer, HDFF effectively leverages their collective strengths. This approach achieved a final score of 0.96852 on the competition's private leaderboard, securing the 20th position out of 184 teams, demonstrating the efficacy of hierarchical fusion for complex image classification tasks.