Few-Shot Learner Generalizes Across AI-Generated Image Detection
This addresses the challenge of generalizing fake image detection across diverse AI models for applications in media verification and security, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of AI-generated image detectors performing poorly on unseen generative models and requiring expensive data collection, proposing a few-shot detector that achieves state-of-the-art performance with +11.6% average accuracy on the GenImage dataset using only 10 additional samples.
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.