仅用10张样本，就能高效识别未知生成模型的假图。
Few-Shot Learner Generalizes Across AI-Generated Image Detection
- 基于少量样本构建专用度量空间，区分真假图像。
- 在GenImage数据集上提升11.6%平均准确率。
- 无需再训练，就能捕捉未见模型的共性特征。
当前基于大规模合成图像数据集训练的假图像检测器，在有限生成模型上表现良好，但对未见过的模型性能显著下降。此外，从在线生成模型中收集足够训练数据往往成本高昂或不可行。为此，我们提出少样本检测器（FSD），一种新型AI生成图像检测方法，通过极少量样本学习专用度量空间，有效区分未见假图像。实验表明，FSD在仅增加10个样本的情况下，于GenImage数据集上实现平均准确率提升11.6%，达到当前最优水平。更重要的是，该方法无需额外训练即可更好捕捉未见图像的类别内共性。代码已开源。
原文摘要 · Abstract (English)
Current fake image detectors trained on large synthetic image datasets perform satisfactorily on limited studied generative models. However, these detectors suffer a notable performance decline over unseen models. Besides, collecting adequate training data from online generative models is often expensive or infeasible. To overcome these issues, we propose Few-Shot Detector (FSD), a novel AI-generated image detector which learns a specialized metric space for effectively distinguishing unseen fake images using very few samples. Experiments show that FSD achieves state-of-the-art performance by $+11.6\%$ average accuracy on the GenImage dataset with only $10$ additional samples. More importantly, our method is better capable of capturing the intra-category commonality in unseen images without further training. Our code is available at https://github.com/teheperinko541/Few-Shot-AIGI-Detector.
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。