UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localization
This provides a comprehensive benchmark for researchers working on AI-generated image detection, addressing gaps in coverage but is incremental as it builds on existing detection efforts.
The authors tackled the problem of limited benchmarks for AI-generated image detection by introducing UniAIDet, a unified benchmark covering diverse generative models and image categories, and used it to evaluate detection methods and answer key research questions.
With the rapid proliferation of image generative models, the authenticity of digital images has become a significant concern. While existing studies have proposed various methods for detecting AI-generated content, current benchmarks are limited in their coverage of diverse generative models and image categories, often overlooking end-to-end image editing and artistic images. To address these limitations, we introduce UniAIDet, a unified and comprehensive benchmark that includes both photographic and artistic images. UniAIDet covers a wide range of generative models, including text-to-image, image-to-image, image inpainting, image editing, and deepfake models. Using UniAIDet, we conduct a comprehensive evaluation of various detection methods and answer three key research questions regarding generalization capability and the relation between detection and localization. Our benchmark and analysis provide a robust foundation for future research.