AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection

Md Redwanul Haque, Manzur Murshed, Manoranjan Paul, Tsz-Kwan Lee

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 0 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 FAIR (SCS prior during training)PatchCraft · GenImage meanaccuracy (%): 82.36 -> 90.40Improved
add FAIRAIDE · GenImage meanaccuracy (%): 86.88 -> 91.01Improved
add FAIRAIDE · AIGCDetect meanaccuracy (%): 93.02 -> 92.14Hurt
add FAIRPatchCraft · Fake2M meanaccuracy (%): 80.46 -> 78.82Hurt
add FAIRAIDE · Fake2M meanaccuracy (%): 69.12 -> 76.18Improved
add FAIRPatchCraft · DRCT-2M meanaccuracy (%): 71.39 -> 74.39Improved
add FAIRAIDE · DRCT-2M meanaccuracy (%): 66.68 -> 68.83Improved
add FAIRAIDE · GenImage BigGANaccuracy (%): 66.89 -> 78.18Improved
add FAIRAIDE · GenImage source domain SDv1.4accuracy (%): 99.74 -> 99.63No clear effect
add dropout p=0.5 (ablation)AIDE · GenImage meanaccuracy (%): 86.9 -> 86.5No clear effect
add L1 penalty 1e-2 (ablation)AIDE · GenImage meanaccuracy (%): 86.9 -> 50.0Hurt
add L2 penalty 1e-2 (ablation)AIDE · GenImage meanaccuracy (%): 86.9 -> 85.0Hurt

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