A Face Forgery Video Detection Model Based on Knowledge Distillation
Haobo Liang, Yingxiong Leng, Jinman Luo, Jie Chen, Xiaoji Guo · 2024
With the rapid evolution of artificial intelligence (AI), face forgery videos have proliferated, posing significant societal challenges. Traditional detection methods struggle with poor generalization and cross-database accuracy, unable to address subtle features and variations in face images across scales and compression levels. This paper reviews current face forgery detection methods, identifying key limitations. It introduces a novel model enhancing features through knowledge distillation, optimizing generalization and robustness via a unique loss function and temperature adjustment strategy. Additionally, a Discrete Cosine Transform with multi-scale and multi-compression capabilities (DCTMS) is integrated, enriching texture and detail capture. Experimental results on deepfake datasets demonstrate the efficacy of the proposed methods, achieving high detection accuracy and robustness across diverse scenarios, including cross-database experiments. This study contributes valuable insights and techniques to advance the field of face forgery detection, addressing risks associated with manipulated video content.