arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.20020cs.CVcs.LG
收藏

ImagiNet:面向合成图像检测的多内容基准数据集

ImagiNet: A Multi-Content Benchmark for Synthetic Image Detection

Stanford University(斯坦福大学)

Delyan Boychev, Radostin Cholakov

AI总结:

针对现有合成图像检测数据集内容单一、检测器泛化性差的问题,提出多内容基准数据集ImagiNet,构建双轨评估体系,训练的基线模型性能优异且泛化性强,同时公开代码与数据。

摘要:

近期的生成模型所产出的图像真实度极高,几乎无法与真实照片和艺术作品区分。这类模型存在潜在的有害应用场景,因此亟需构建鲁棒的合成图像检测器。但当前该领域的数据集要么包含的生成图像质量存疑,要么样本以单一内容类型为主,导致检测器的泛化性能较差。我们发现,在各类内容类型中均衡构建高分辨率生成图像集合,对提升检测器的泛化能力至关重要,因此提出ImagiNet数据集,该数据集包含20万样本,覆盖照片、绘画、人脸和杂项四大类别。ImagiNet中的合成图像由开源和专有生成器共同生成,各类别对应的真实图像则从公开数据集中收集。ImagiNet的结构支持双轨评估体系:i)真实/合成图像分类;ii)生成模型识别。为建立强基线,我们针对每个轨道采用自监督对比目标(SelfCon)训练ResNet-50模型,该模型即使在存在压缩和缩放的条件下,评估AUC最高可达0.99,平衡准确率在86%到95%之间。所提供的模型泛化能力足够强,在以往的合成检测基准上取得了零样本的最优性能。我们还通过消融实验证明了内容类型的重要性,并公开了代码和数据。

英文摘要:

Recent generative models produce images with a level of authenticity that makes them nearly indistinguishable from real photos and artwork. Potential harmful use cases of these models, necessitate the creation of robust synthetic image detectors. However, current datasets in the field contain generated images with questionable quality or have examples from one predominant content type which leads to poor generalizability of the underlying detectors. We find that the curation of a balanced amount of high-resolution generated images across various content types is crucial for the generalizability of detectors, and introduce ImagiNet, a dataset of 200K examples, spanning four categories: photos, paintings, faces, and miscellaneous. Synthetic images in ImagiNet are produced with both open-source and proprietary generators, whereas real counterparts for each 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 strong baseline, we train a ResNet-50 model using a self-supervised contrastive objective (SelfCon) for each track which achieves evaluation AUC of up to 0.99 and balanced accuracy ranging from 86% to 95%, even under conditions that involve compression and resizing. The provided model is generalizable enough to achieve zero-shot state-of-the-art performance on previous synthetic detection benchmarks. We provide ablations to demonstrate the importance of content types and publish code and data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑