← Search

Jaeho Yoon

2 accepted papers

2025

TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

CVPR 2025poster

We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing models suffer from tail-versus-noise trade-off where if a mode…

2023

Understanding the Feature Norm for Out-of-Distribution Detection

ICCV 2023poster

A neural network trained on a classification dataset often exhibits a higher vector norm of hidden layer features for in-distribution (ID) samples, while producing relatively lower norm values on unseen instances from out-of-distribution (OOD). Despite this intriguing phenomenon being utilized in ma…

Cited by 16PDFScholar