Normality Learning

Normality learning in machine learning focuses on building models that accurately represent typical data patterns to effectively identify anomalies or deviations. Current research emphasizes developing robust methods for learning normal patterns, even with noisy or incomplete data, using techniques like contrastive learning, teacher-student networks, and adaptive thresholding within various architectures including autoencoders and vision-language models. This field is crucial for improving anomaly detection across diverse applications, such as industrial quality control, cybersecurity, and video surveillance, where identifying unusual events is critical for safety and efficiency. The development of more accurate and efficient normality learning models directly impacts the reliability and performance of these applications.

Papers

October 16, 2024

Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling
Sinong Zhao, Wenrui Wang, Hongzuo Xu, Zhaoyang Yu, Qingsong Wen, Gang Wang, xiaoguang Liu, Guansong Pang
Future Reasoning Context Modeling Long Term Forecasting Time Series Anomaly Detection Normality Learning

July 29, 2024

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models
Jihun Yi, Dahuin Jung, Sungroh Yoon
Image Anomaly Detection Normality Learning Industrial Image Anomaly Detection Normality Addition

February 27, 2024

Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization
Hanqiu Deng, Xingyu Li
Anomaly Detection Localization Focus Visual Anomaly Detection Multi Class Anomaly Detection Anomaly Detection Datasets Normality Learning

September 12, 2023

Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning
Jingcan Duan, Pei Zhang, Siwei Wang, Jingtao Hu, Hu Jin, Jiaxin Zhang, Haifang Zhou, Xinwang Liu
Graph Anomaly Detection Higher Order Network Scale Contrastive Learning Normality Learning

February 20, 2023

Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection
Chaewon Park, Minhyeok Lee, Suhwan Cho, Donghyeong Kim, Sangyoun Lee
Industrial Anomaly Detection Two Stream Reconstruction Based Anomaly Detection Unveiling Hidden Energy Anomaly Normality Learning

February 13, 2023

Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
Anomaly Detection Training Dynamic One Class Classification Deep Anomaly Detection Adaptive Threshold Normality Learning

September 24, 2022

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
Zhengwei Fang, Rui Wang, Tao Huang, Liping Jing
Adversarial Example Adversarial Perturbation Transferable Adversarial Attack Perturbation Attack Normality Learning

July 25, 2022

Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection
Hongzuo Xu, Yijie Wang, Songlei Jian, Qing Liao, Yongjun Wang, Guansong Pang
Anomaly Detection Unsupervised Time Series Anomaly Detection Calibrated Learning Normality Learning Calibration Network

March 7, 2022

Object-centric and memory-guided normality reconstruction for video anomaly detection
Khalil Bergaoui, Yassine Naji, Aleksandr Setkov, Angélique Loesch, Michèle Gouiffès, Romaric Audigier
Anomaly Detection Video Anomaly Detection Video Surveillance Normality Learning

February 13, 2022

RandomSEMO: Normality Learning Of Moving Objects For Video Anomaly Detection
Chaewon Park, Minhyeok Lee, MyeongAh Cho, Sangyoun Lee
Supervised Autoencoder Video Anomaly Detection Random Participation Adjacent Superpixels Superpixel Method Moving Object Normality Learning

Normality Learning

Papers

Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models

Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization

Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning

Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection

Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection

Object-centric and memory-guided normality reconstruction for video anomaly detection

RandomSEMO: Normality Learning Of Moving Objects For Video Anomaly Detection