SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection
This work addresses the problem of identifying AI-generated images for security and verification purposes, representing an incremental improvement in detection methods.
The paper tackled the detection of AI-generated images by fine-tuning a Vision Transformer with data augmentation, achieving state-of-the-art performance that significantly outperformed competing methods on validation and test datasets.
The aim of this work is to explore the potential of pre-trained vision-language models, e.g. Vision Transformers (ViT), enhanced with advanced data augmentation strategies for the detection of AI-generated images. Our approach leverages a fine-tuned ViT model trained on the Defactify-4.0 dataset, which includes images generated by state-of-the-art models such as Stable Diffusion 2.1, Stable Diffusion XL, Stable Diffusion 3, DALL-E 3, and MidJourney. We employ perturbation techniques like flipping, rotation, Gaussian noise injection, and JPEG compression during training to improve model robustness and generalisation. The experimental results demonstrate that our ViT-based pipeline achieves state-of-the-art performance, significantly outperforming competing methods on both validation and test datasets.