AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection

Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac

AAAI 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 2 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 assignment loss (Sinkhorn clustering) to binary loss (ablation)TriDetect · ChameleonAUC: 0.8033 -> 0.8560Improved
add consistency loss on top of assignment loss (ablation)TriDetect · ChameleonAUC: 0.8560 -> 0.8935Improved
add consistency loss on top of assignment loss (ablation)TriDetect · ChameleonACC: 0.6335 -> 0.6258 vs binary onlyHurt
add both clustering losses (ablation)TriDetect · ChameleonEER: 0.2713 -> 0.1843Improved
set beta to 0.7 rather than 0.3 (ablation)TriDetect · ChameleonAUC: 0.8423 -> 0.8935Improved
set beta to 0.9 rather than 0.7 (ablation)TriDetect · ChameleonAUC: 0.8935 -> 0.8774Hurt
TriDetect vs Effort on WildFakeTriDetect · WildFakeavg ACC: 0.7522 -> 0.8254Improved
TriDetect vs Effort on AIGCDetectBenchmarkTriDetect · AIGCDetectBenchmarkavg AUC: 0.9783 -> 0.9869Improved

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