AI RESEARCH
Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models
arXiv CS.CV
•
ArXi:2602.01738v2 Announce Type: replace While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse in realistic, in-the-wild scenarios. In this work, we nstrate that simplicity prevails over complex architectural designs. A simple linear classifier trained on the frozen features of modern Vision Foundation Models, including Perception Encoder, MetaCLIP 2, and DINOv3, establishes a new state-of-the-art.