Improve model card: Add pipeline tag, links, abstract, and citation

README.md

@@ -1,8 +1,10 @@
 ---
-license: cc-by-nc-sa-4.0
 datasets:
 - HorizonTEL/AIGIBench
+license: cc-by-nc-sa-4.0
+pipeline_tag: image-classification
 ---
+
 <div align="center">
  <br>
 <h1>Is Artificial Intelligence Generated Image Detection a Solved Problem?</h1>
@@ -19,10 +21,32 @@ datasets:
 <sup>1</sup>Nanjing University of Information Science and Technology <sup>2</sup>University of Siena
 </div>
 
+This model contains the official pre-trained checkpoints of the AIGIBench, as described in the paper [Is Artificial Intelligence Generated Image Detection a Solved Problem?](https://huggingface.co/papers/2505.12335).
+
+- 📚 Paper: [Is Artificial Intelligence Generated Image Detection a Solved Problem?](https://huggingface.co/papers/2505.12335)
+- 💻 Code: [https://github.com/HorizonTEL/AIGIBench](https://github.com/HorizonTEL/AIGIBench)
+- 🌐 Project Page: [https://github.com/HorizonTEL/AIGIBench](https://github.com/HorizonTEL/AIGIBench)
+
+## Abstract
 
-**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.
+The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although numerous Artificial Intelligence Generated Image (AIGI) detectors have been proposed, often reporting high accuracy, their effectiveness in real-world scenarios remains questionable. To bridge this gap, we introduce AIGIBench, a comprehensive benchmark designed to rigorously evaluate the robustness and generalization capabilities of state-of-the-art AIGI detectors. AIGIBench simulates real-world challenges through four core tasks: multi-source generalization, robustness to image degradation, sensitivity to data augmentation, and impact of test-time pre-processing. It includes 23 diverse fake image subsets that span both advanced and widely adopted image generation techniques, along with real-world samples collected from social media and AI art platforms. Extensive experiments on 11 advanced detectors demonstrate that, despite their high reported accuracy in controlled settings, these detectors suffer significant performance drops on real-world data, limited benefits from common augmentations, and nuanced effects of pre-processing, highlighting the need for more robust detection strategies. By providing a unified and realistic evaluation framework, AIGIBench offers valuable insights to guide future research toward dependable and generalizable AIGI detectors. Models and code are publicly available at: this https URL .
+
+## Model Description
+
+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.
 
 If this project helps you, please fork, watch, and give a star to this repository.  
 
+## Citation
+
+```bibtex
+@inproceedings{li2025artificial,
+  title={Is Artificial Intelligence Generated Image Detection a Solved Problem?},
+  author={Li, Ziqiang and Yan, Jiazhen and He, Ziwen and Zeng, Kai and Jiang, Weiwei and Xiong, Lizhi and Fu, Zhangjie},
+  booktitle={Advances in Neural Information Processing Systems},
+  year={2025}
+}
+```
+
 ## Contact
 If you have any question about this project, please feel free to contact 247918horizon@gmail.com