AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

FuDU: A Fuzzy Dual-dimension Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection

Zhaoyang Wang, Haiyong Chen, Binyi Su, Xinwei Lyu

ECCV 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty

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
replace confidence sampling with FuDU fuzzy dual-uncertainty samplingRT-DETR streaming AL · Nuclear fuel rod defectsmean mAP50: 87.2 -> 92.2Improved
use FuDU instead of confidence across backbones and detection headsSwin, ViTDet, DEIM, MR-DETR, MI-DETR · Nuclear fuel rod defectsmean mAP50: 87.3 -> 91.6 (Swin); 86.6 -> 93.2 (MI-DETR)Improved
set prototype count k to 50 rather than 10 (ablation)PGUQ · Nuclear fuel rod defectssampling ratio: 40.5% -> 15.4% with mAP 92.0 -> 92.2Improved
set prototype count k to 50 rather than 100 (ablation)PGUQ · Nuclear fuel rod defectsmean mAP50: 88.5 -> 92.2Improved
learnable end-to-end prototypes instead of re-clustering each round (ablation)PGUQ · Nuclear fuel rod defectsmean mAP50: 90.8 -> 92.2Improved
prototype distance instead of reconstruction-based global uncertainty (ablation)PGUQ · Nuclear fuel rod defectsmean mAP50: 89.7 (CD), 88.8 (FAE) -> 92.2Improved
add defect uncertainty Ud to global uncertainty (ablation)FuDU · Nuclear fuel rod defectsmean mAP50: 89.6 -> 92.2Improved
add localization entropy weight (w2=2) with classification entropy (ablation)DeUE · Nuclear fuel rod defectsmean mAP50: 90.2 -> 92.2Improved
increase classification entropy weight to 2 (ablation)DeUE · Nuclear fuel rod defectsmean mAP50: 91.7 -> 89.8Hurt
increase localization weight to 4 (ablation)DeUE · Nuclear fuel rod defectssampling ratio: 15.4% -> 17.3% (mAP 92.2 -> 92.1)Hurt
fuzzy inference sampling instead of hard threshold (ablation)FuDU · Nuclear fuel rod defectsmean mAP50 / ratio: 92.0 -> 92.2; P 88.2 -> 95.1Improved
fuzzy inference instead of sigmoid mapping (ablation)FuDU · Nuclear fuel rod defectssampling ratio: 23.4% -> 15.4%Improved

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