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.
@article{arxiv.2503.18812,
title = {SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection},
author = {Shrikant Malviya and Neelanjan Bhowmik and Stamos Katsigiannis},
journal= {arXiv preprint arXiv:2503.18812},
year = {2025}
}
Comments
De-Factify 4.0 workshop at the 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025)