Saved in:
Bibliographic Details
Main Author: Ou, Ziyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.10664
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915289644400640
author Ou, Ziyang
author_facet Ou, Ziyang
contents Verifying the authenticity of AI-generated images presents a growing challenge on social media platforms these days. While vision-language models (VLMs) like CLIP outdo in multimodal representation, their capacity for AI-generated image classification is underexplored due to the absence of such labels during the pre-training process. This work investigates whether CLIP embeddings inherently contain information indicative of AI generation. A proposed pipeline extracts visual embeddings using a frozen CLIP model, feeds its embeddings to lightweight networks, and fine-tunes only the final classifier. Experiments on the public CIFAKE benchmark show the performance reaches 95% accuracy without language reasoning. Few-shot adaptation to curated custom with 20% of the data results in performance to 85%. A closed-source baseline (Gemini-2.0) has the best zero-shot accuracy yet fails on specific styles. Notably, some specific image types, such as wide-angle photographs and oil paintings, pose significant challenges to classification. These results indicate previously unexplored difficulties in classifying certain types of AI-generated images, revealing new and more specific questions in this domain that are worth further investigation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLIP Embeddings for AI-Generated Image Detection: A Few-Shot Study with Lightweight Classifier
Ou, Ziyang
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.10
Verifying the authenticity of AI-generated images presents a growing challenge on social media platforms these days. While vision-language models (VLMs) like CLIP outdo in multimodal representation, their capacity for AI-generated image classification is underexplored due to the absence of such labels during the pre-training process. This work investigates whether CLIP embeddings inherently contain information indicative of AI generation. A proposed pipeline extracts visual embeddings using a frozen CLIP model, feeds its embeddings to lightweight networks, and fine-tunes only the final classifier. Experiments on the public CIFAKE benchmark show the performance reaches 95% accuracy without language reasoning. Few-shot adaptation to curated custom with 20% of the data results in performance to 85%. A closed-source baseline (Gemini-2.0) has the best zero-shot accuracy yet fails on specific styles. Notably, some specific image types, such as wide-angle photographs and oil paintings, pose significant challenges to classification. These results indicate previously unexplored difficulties in classifying certain types of AI-generated images, revealing new and more specific questions in this domain that are worth further investigation.
title CLIP Embeddings for AI-Generated Image Detection: A Few-Shot Study with Lightweight Classifier
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.10
url https://arxiv.org/abs/2505.10664