AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes

Ziheng Qin, Yuheng Ji, Renshuai Tao, Yuxuan Tian, Yuyang Liu, Yipu Wang, Xiaolong Zheng

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add prototype mapping (cross-attention to prototypes) (ablation)GAPL w/o PCA, LoRA · 4-benchmark meanmAcc: 60.05 -> 68.59Improved
add PCA-derived generator-aware prototypes to prototype mapping (ablation)GAPL w/o LoRA · 4-benchmark meanmAcc: 68.59 -> 71.88Improved
add LoRA finetuning to prototype mapping (ablation)GAPL · 4-benchmark meanmAcc: 68.59 -> 90.35Improved
add PCA prototypes on top of PM + LoRA (ablation)GAPL · 4-benchmark meanmAcc: 90.35 -> 95.54Improved
add LoRA alone (no PM, no PCA) (ablation)GAPL · 4-benchmark meanmAcc: 60.05 -> 88.52Improved
use PM+LoRA without PCA, mAP (ablation)GAPL · 4-benchmark meanmAP: 97.91 -> 95.40 (LoRA only vs PM+LoRA); full 98.97Mixed
increase number of prototypes from 16 to 64 (ablation)GAPL · 4-benchmark meanmAcc: 95.28 -> 95.54No clear effect
build prototypes from real generator types instead of random vectors (ablation)GAPL · 4-benchmark meanmAcc: 90.35 -> 95.54 (3 types)Improved
add a fourth generator type to prototype set (ablation)GAPL · 4-benchmark meanmAcc: 95.54 -> 95.29No clear effect
train all detectors on large multi-generator data (scaling up)previous AIGI detectors (e.g. Co-SPY, NPR, UniFD) · 4-benchmark meanaccuracy: e.g. UniFD 59.8 vs Swin-T 89.7Hurt
use GAPL rather than CommForen with 4.7K generatorsGAPL · 6-benchmark meanaccuracy: 86.9 -> 90.4Improved
GAPL on Chameleon vs B-FreeGAPL · Chameleonaccuracy: 78.2 -> 71.0Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy