Raising the Bar of AI-generated Image Detection with CLIP

arXiv:2312.00195v2 Announce Type: replace
Abstract: The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios. We find that, contrary to previous beliefs, it is neither necessary nor convenient to use a large domain-specific dataset for training. On the contrary, by using only a handful of example images from …

ai-generated image arxiv clip cs.cv detection generated image image detection type