AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples

Shiyu Wu, Shuyan Li, Jing Li, Jing Liu, Yequan Wang

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 9 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
use the OmniDFA metric-learning model instead of prototypical classification on backbones of existing detectors/attributorsfew-shot attribution · OmniFake 5-way 10-shotaccuracy: 73.31 -> 75.34 (vs FSD)Improved
use OmniDFA instead of FSD on 15-way attributionfew-shot attribution · OmniFake 15-way 10-shotaccuracy: 52.28 -> 53.54 average; Part III 60.81 -> 60.26Mixed
train detectors on diverse multi-generator data rather than single-generator dataAIGI detection · OmniFake detectionaccuracy: 57.24 (UnivFD) vs 95.58 (OmniDFA)Improved
add sphere center loss on real class plus Tukey boundary threshold for detectionOmniDFA · OmniFake detectionaccuracy: avg Acc 95.58 vs ComFor 89.75; real acc 95.32 vs ComFor 98.96Mixed
OmniDFA vs prior detectors under zero-shot ChameleonOmniDFA · Chameleonaccuracy: 65.77 -> 83.48Improved
OmniDFA on GenImage zero-shotOmniDFA · GenImageaccuracy: 90.53 -> 95.86 (average vs AIDE)Improved
increase support shots from 1 to 10 per class (ablation)OmniDFA · OmniFake attributionaccuracyImproved
increase support shots beyond 10 up to 200 (ablation)OmniDFA · OmniFake attributionaccuracyNo clear effect
use dual-branch (local and global) instead of single-branch (ablation)OmniDFA · OmniFake detection and attributionaccuracyImproved
use supervised contrastive learning instead of plain binary classifier (ablation)OmniDFA · OmniFake detectionaccuracyImproved
train with JPEG and blur augmentation (ablation)OmniDFA · OmniFake Part I robustnessaccuracyMixed

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