Anomaly Class

Anomaly class detection focuses on identifying unusual data points that deviate significantly from the norm, a crucial task across diverse fields. Current research emphasizes developing robust methods that can handle both known and unknown anomaly types ("open-set" detection), often employing deep learning architectures like Siamese networks and multi-head networks to learn effective representations from limited labeled data. These advancements are improving anomaly detection accuracy and efficiency in applications ranging from fraud detection to astronomical data analysis, enabling more effective monitoring and decision-making in complex systems. The integration of human-in-the-loop approaches further enhances the practical applicability of these techniques, particularly in high-stakes scenarios.

Papers

January 13, 2025

Anomalous Agreement: How to find the Ideal Number of Anomaly Classes in Correlated, Multivariate Time Series Data
Ferdinand Rewicki, Joachim Denzler, Julia Niebling
Data Clustering Multivariate Time Series Data Minimum Number Clustering Quality Correlated Source Anomaly Class

November 25, 2024

ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shift
Hossein Kashiani, Niloufar Alipour Talemi, Fatemeh Afghah
Anomaly Detection Internet Service Domain Built Road Two Shift Multi Class Anomaly Detection Anomaly Detector Anomaly Class

October 18, 2023

Open-Set Multivariate Time-Series Anomaly Detection
Thomas Lai, Thi Kieu Khanh Ho, Narges Armanfard
Anomaly Detection Open Set Anomaly Score Time Series Feature Anomaly Class

June 26, 2023

Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
Yujiang Pu, Xiaoyu Wu, Lulu Yang, Shengjin Wang
LeArning Abstract Prompt Learning Weak Supervision Video Anomaly Detection Graph Convolution Network Weakly Supervised Video Anomaly Detection Anomaly Detection Framework Anomaly Class

April 6, 2023

From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management
Xueying Ding, Nikita Seleznev, Senthil Kumar, C. Bayan Bruss, Leman Akoglu
Line by Line Explanation Human in the Loop Action Feature Anomaly Class

January 17, 2023

FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks
Niamh Belton, Misgina Tsighe Hagos, Aonghus Lawlor, Kathleen M. Curran
Anomaly Detection Siamese Network MNIST Canadian Institute for Advanced Anomaly Class

November 1, 2022

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection
Aleksandra Ćiprijanović, Ashia Lewis, Kevin Pedro, Sandeep Madireddy, Brian Nord, Gabriel N. Perdue, Stefan M. Wild
Anomaly Detection Domain Adaptation Domain Alignment Semi Supervised Domain Adaptation Universal Domain Adaptation Galaxy Morphology Anomaly Class

October 28, 2022

Learning to Detect Interesting Anomalies
Alireza Vafaei Sadr, Bruce A. Bassett, Emmanuel Sekyi
LeArning Abstract Outlier Detection Anomaly Detection Algorithm Anomaly Class

March 28, 2022

Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
Choubo Ding, Guansong Pang, Chunhua Shen
Anomaly Detection Open Set Grayscale Image Anomaly Detection Datasets Supervised Anomaly Detection Anomaly Class