Few-Shot Learner Generalizes Across AI-Generated Image Detection

doi:10.48550/arXiv.2501.08763

Paper

Few-Shot Learner Generalizes Across AI-Generated Image Detection

Published Jan 15, 2025 · Shiyu Wu, Jing Liu, Jing Li

ArXiv

0

Citations

0

Influential Citations

PDF

Abstract

Current fake image detectors trained on large synthetic image datasets perform satisfactorily on limited studied generative models. However, they 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 to effectively distinguish unseen fake images by utilizing very few samples. Experiments show FSD achieves state-of-the-art performance by $+7.4\%$ average ACC on GenImage dataset. More importantly, our method is better capable of capturing the intra-category common features in unseen images without further training.

Preprint

Study Snapshot

Few-Shot Detector (FSD) effectively distinguishes unseen fake images by learning a specialized metric space, improving performance on GenImage dataset by 7.4%.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Few-Shot Learner Generalizes Across AI-Generated Image Detection

References

Citations