Fusing Global and Local Features for Generalized AI-Synthesized Image Detection

TL;DR

This paper introduces a two-branch model that fuses global and local features using attention mechanisms to improve the generalization of AI-synthesized image detection across unseen models and diverse datasets.

Contribution

It proposes a novel patch selection and multi-head attention-based fusion approach to enhance detection accuracy and generalization in real-world scenarios.

Findings

High detection accuracy on diverse datasets

Strong generalization to unseen GAN models

Effective fusion of global and local features

Abstract

With the development of the Generative Adversarial Networks (GANs) and DeepFakes, AI-synthesized images are now of such high quality that humans can hardly distinguish them from real images. It is imperative for media forensics to develop detectors to expose them accurately. Existing detection methods have shown high performance in generated images detection, but they tend to generalize poorly in the real-world scenarios, where the synthetic images are usually generated with unseen models using unknown source data. In this work, we emphasize the importance of combining information from the whole image and informative patches in improving the generalization ability of AI-synthesized image detection. Specifically, we design a two-branch model to combine global spatial information from the whole image and local informative features from multiple patches selected by a novel patch selection module. Multi-head attention mechanism is further utilized to fuse the global and local features. We collect a highly diverse dataset synthesized by 19 models with various objects and resolutions to evaluate our model. Experimental results demonstrate the high accuracy and good generalization ability of our method in detecting generated images. Our code is available at https://github.com/littlejuyan/FusingGlobalandLocal.