SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Malviya, Shrikant, Bhowmik, Neelanjan, Katsigiannis, Stamos
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912290707603456
author Malviya, Shrikant
Bhowmik, Neelanjan
Katsigiannis, Stamos
author_facet Malviya, Shrikant
Bhowmik, Neelanjan
Katsigiannis, Stamos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18812
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection
Malviya, Shrikant
Bhowmik, Neelanjan
Katsigiannis, Stamos
Computer Vision and Pattern Recognition
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.
title SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.18812