TwinSynths

该数据集名为TwinSynths，它是一种新的基准生成方法，通过构建视觉上几乎相同的真实图像和合成图像对来确保高质量和内容保持。TwinSynths主要关注图像质量、内容保持以及类别多样性，其任务是对人工智能生成的图像进行检测。

This dataset, named TwinSynths, is a novel benchmark generation method that constructs nearly visually identical pairs of real and synthetic images to ensure high quality and content preservation. TwinSynths primarily focuses on image quality, content preservation, and category diversity, with its core task being the detection of AI-generated images.