Abstract
The extraordinary ability of generative models to generate photographic images has intensified concerns about the spread of disinformation, thereby leading to the demand for detectors capable of distinguishing between AI-generated fake images and real images. However, the lack of large datasets containing images from the most advanced image generators poses an obstacle to the development of such detectors. In this paper, we introduce the GenImage dataset, which has the following advantages: 1) Plenty of Images, including over one million pairs of AI-generated fake images and collected real images. 2) Rich Image Content, encompassing a broad range of image classes. 3) State-of-the-art Generators, synthesizing images with advanced diffusion models and GANs. The aforementioned advantages allow the detectors trained on GenImage to undergo a thorough evaluation and demonstrate strong applicability to diverse images. We conduct a comprehensive analysis of the dataset and propose two tasks for evaluating the detection method in resembling real-world scenarios. The cross-generator image classification task measures the performance of a detector trained on one generator when tested on the others. The degraded image classification task assesses the capability of the detectors in handling degraded images such as low-resolution, blurred, and compressed images. With the GenImage dataset, researchers can effectively expedite the development and evaluation of superior AI-generated image detectors in comparison to prevailing methodologies.
Example
Website Status
This Website is still updating.
BibTeX
@misc{zhu2023genimage,
title={GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image},
author={Mingjian Zhu and Hanting Chen and Qiangyu Yan and Xudong Huang and Guanyu Lin and Wei Li and Zhijun Tu and Hailin Hu and Jie Hu and Yunhe Wang},
year={2023},
eprint={2306.08571},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
License
Unless specifically labeled otherwise, these Datasets are provided to You under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License (“CC BY-NC-SA 4.0”), with the additional terms included herein. The CC BY-NC-SA 4.0 may be accessed at https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode. When You download or use the Datasets from the Website or elsewhere, You are agreeing to comply with the terms of CC BY-NC-SA 4.0, and also agreeing to the Dataset Terms. Where these Dataset Terms conflict with the terms of CC BY-NC-SA 4.0, these Dataset Terms shall prevail. We reiterate once again that this dataset is used only for non-commercial purposes such as academic research, teaching, or scientific publications. We prohibits You from using the dataset or any derivative works for commercial purposes, such as selling data or using it for commercial gain.