Skip to main content

Anomaly Detection

ResAD: A Simple Framework for Class Generalizable Anomaly Detection
·2059 words·10 mins· loading · loading
Anomaly Detection 🏢 Shanghai Jiao Tong University
ResAD, a novel framework, tackles class-generalizable anomaly detection by learning residual feature distributions, achieving remarkable results on diverse datasets without retraining.
One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
·2365 words·12 mins· loading · loading
Computer Vision Anomaly Detection 🏢 West China Biomedical Big Data Center, West China Hospital, Sichuan University
One-to-Normal: Anomaly personalization boosts few-shot anomaly detection accuracy by transforming query images to match normal data, enabling precise, robust comparisons and flexible integration with …
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
·3318 words·16 mins· loading · loading
AI Generated Computer Vision Anomaly Detection 🏢 Zhejiang University Youtu Lab
MambaAD: Linear-complexity multi-class unsupervised anomaly detection using a novel Mamba-based decoder with Locality-Enhanced State Space modules.