ImagiNet：用于通过对比学习实现通用合成图像检测的多内容数据集

ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning

July 29, 2024

作者: Delyan Boychev, Radostin Cholakov

cs.AI

摘要

生成模型，如扩散模型（DMs），变分自动编码器（VAEs）和生成对抗网络（GANs），能够生成具有接近真实照片和艺术作品水准的图像。尽管这种能力对许多行业都有益，但识别合成图像的困难使在线媒体平台容易受到冒充和误导的攻击。为了支持防御方法的发展，我们引入了ImagiNet，这是一个用于合成图像检测的高分辨率和平衡数据集，旨在减轻现有资源中潜在的偏见。该数据集包含20万个示例，涵盖四个内容类别：照片、绘画、人脸和未分类。合成图像是使用开源和专有生成器生成的，而相同内容类型的真实对应图像则来自公共数据集。ImagiNet的结构允许建立一个双轨评估系统：i）分类为真实或合成图像，ii）识别生成模型。为建立基准，我们针对每个轨道使用自监督对比目标（SelfCon）训练了一个ResNet-50模型。该模型在已建立的基准测试中表现出最先进的性能和高推理速度，实现了高达0.99的AUC和在86%至95%之间的平衡准确率，即使在涉及压缩和调整大小的社交网络条件下也是如此。我们的数据和代码可在https://github.com/delyan-boychev/imaginet 获取。

English

Generative models, such as diffusion models (DMs), variational autoencoders (VAEs), and generative adversarial networks (GANs), produce images with a level of authenticity that makes them nearly indistinguishable from real photos and artwork. While this capability is beneficial for many industries, the difficulty of identifying synthetic images leaves online media platforms vulnerable to impersonation and misinformation attempts. To support the development of defensive methods, we introduce ImagiNet, a high-resolution and balanced dataset for synthetic image detection, designed to mitigate potential biases in existing resources. It contains 200K examples, spanning four content categories: photos, paintings, faces, and uncategorized. Synthetic images are produced with open-source and proprietary generators, whereas real counterparts of the same content type are collected from public datasets. The structure of ImagiNet allows for a two-track evaluation system: i) classification as real or synthetic and ii) identification of the generative model. To establish a baseline, we train a ResNet-50 model using a self-supervised contrastive objective (SelfCon) for each track. The model demonstrates state-of-the-art performance and high inference speed across established benchmarks, achieving an AUC of up to 0.99 and balanced accuracy ranging from 86% to 95%, even under social network conditions that involve compression and resizing. Our data and code are available at https://github.com/delyan-boychev/imaginet.