A LoRA-enhanced vision transformer for generalized and robust continual face forgery detection

• Main Author: Wu, Yulong
• Other Authors: Alex Chichung Kot
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2025
• Subjects: Computer and Information Science; LoRA; Face forgery detection
• Online Access: https://hdl.handle.net/10356/182478
• Institution: Nanyang Technological University

In this dissertation, we present an efficient training method for face forgery detection models by combining Low-rank adaptation (LoRA) with Vision Transformers (ViT). The approach facilitates continual learning across multiple face forgery datasets organized by their release dates, followed by testing on all training datasets and an unseen dataset. Our findings indicate that the LoRA technique significantly reduces computation and storage costs while alleviating the issue of catastrophic forgetting. Additionally, through experiments varying the amount of training data, we demonstrate that the ViT model with LoRA provides the best stability and generalization, particularly in the context of emerging face forgery detection techniques.