Problem
Research questions and friction points this paper is trying to address.
AI-generated image detection
generator shift
feature space
Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection
๐ค AI Summary
็ ็ฉถ้่ฟ่ฎญ็ปๅ
้ชๆกไปถ็้ซๆฏๅคๅซๆจกๅ๏ผ่งฃๅณAI็ๆๅพๅๆฃๆตๅจไธๅ็ๆๅจใๆ็คบ/้ฃๆ ผๅๆบๅๅๅไธ็ๆณๅ้ฎ้ขใ
๐ Abstract
Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-generated image detection as a transfer system described by training prior, frozen encoder feature space, and decision rule, and ask when classifier head training adds value beyond what is already separable in modern features. As a controlled diagnostic, we fit a prior-conditioned Gaussian discriminant ladder: closed-form heads built from first- and second-order feature statistics under nested covariance assumptions. On Percept-Lens, a unified protocol over 39 public datasets (7.1 million images), the best rung is frequently competitive with, and sometimes exceeds, released AI-generated image detector heads when matched on both prior and encoder. We further quantify strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Prior-Conditioned Gaussian Discriminants
AI-generated Image Detection
Feature Statistics
Transfer Learning
Data Efficiency
๐ Similar Papers
No similar papers found.
