AIGIBench

<div align="center"> <br> <h1>Is Artificial Intelligence Generated Image Detection a Solved Problem?</h1>

Ziqiang Li¹, Jiazhen Yan¹, Ziwen He¹, Kai Zeng², Weiwei Jiang¹, Lizhi Xiong¹, Zhangjie Fu^1‡

<div class="is-size-6 publication-authors"> <p class="footnote"> <span class="footnote-symbol">^‡</span>Corresponding author </p> </div>

¹Nanjing University of Information Science and Technology ²University of Siena

</div>

This repository is the official pre-trained checkpoints of the AIGIBench in Setting-II: Training on 144K images generated by both SD-v1.4 and ProGAN, covering the same four object categories.

Of course, if you need the code from the original paper, the following is the corresponding detection code in the paper：

• ResNet-50: Deep Residual Learning for Image Recognition
• CNNDetection: CNN-generated images are surprisingly easy to spot...for now
• GramNet: Global Texture Enhancement for Fake Face Detection in the Wild
• LGrad: Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection
• CLIPDetection: Towards Universal Fake Image Detectors that Generalize Across Generative Models
• FreqNet: FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform
• NPR: Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection
• DFFreq: Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection
• LaDeDa: Real-Time Deepfake Detection in the Real-World
• AIDE: A Sanity Check for AI-generated Image Detection
• SAFE: Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectives

If this project helps you, please fork, watch, and give a star to this repository.

Contact

If you have any question about this project, please feel free to contact [email protected]