用少量样本识别未知生成模型，应对快速迭代的AI图像生成挑战
Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples
- 提出少样本溯源新范式，仅需少量样本即可识别未见过的生成器
- 构建含117万张图像的OmniFake数据集，覆盖45种生成器
- 模型在少样本场景下表现优异，适合真实世界快速演化的生成技术追踪
AI生成图像（AIGI）溯源面临严峻挑战，不仅需要检测合成图像，还需定位其来源模型或技术。然而，多数现有方法采用闭集设置，需重新训练才能识别新类别，难以适应图像生成技术的快速演进。本文提出一种新的少样本溯源范式，旨在仅用有限样本可靠识别未知生成器，适用于实际应用。为此，我们构建了OmniFake——一个大规模、细粒度分类的合成图像数据集，包含117万张来自45种不同生成器的图像。进一步提出了OmniDFA（Omni Detector and Few-shot Attributor），作为少样本溯源基线，不仅能判断图像真伪，还能确定其生成来源。实验表明，OmniDFA在少样本溯源任务中表现卓越，在AIGI检测上达到先进水平。相关数据集与代码已公开于https://github.com/teheperinko541/OmniDFA。
原文摘要 · Abstract (English)
AI-generated image (AIGI) attribution presents a pressing challenge that goes beyond mere AIGI detection, aiming to identify the source model or technique responsible for a synthetic image. However, most previous source attribution methods operate in a closed-set manner, which necessitates retraining to recognize any novel category, preventing adaptation to the rapid evolution of image generation. In this work, we propose a new paradigm for synthetic image attribution, termed few-shot attribution. This paradigm targets the reliable identification of unseen generators using only limited samples, making it highly suitable for real-world applications. To facilitate this work, we construct OmniFake, a large-scale, well-categorized synthetic image dataset that contains $1.17$ million images from $45$ distinct generators. We further introduce OmniDFA (Omni Detector and Few-shot Attributor), a few-shot attribution baseline that not only assesses the authenticity of images but also determines their synthesis origins. Experiments demonstrate that OmniDFA exhibits excellent capability in few-shot attribution and achieves state-of-the-art generalization performance in AIGI detection. Our dataset and code are available at https://github.com/teheperinko541/OmniDFA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。