SOTAVerified

One-Class Classification

One-class classification (OCC) algorithms serve a crucial role in scenarios where the negative class is either absent, poorly sampled, or not well defined. This unique situation presents a challenge for building effective classifiers, as they must delineate the class boundary solely based on knowledge of the positive class. OCC has found application in various research domains, including outlier/novelty detection and concept learning.

In the context of anomaly detection, OCC models are trained exclusively on "normal" data and are subsequently tasked with identifying anomalous patterns during inference.

A one-class classifier aims at capturing characteristics of training instances, in order to be able to distinguish between them and potential outliers to appear.

— Page 139, Learning from Imbalanced Data Sets, 2018.

Title	Date	Tasks	Status	Hype
Few-Shot One-Class Classification via Meta-Learning	Jul 8, 2020	Anomaly DetectionClassification	CodeCode Available	1
FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data	Nov 25, 2024	Anomaly DetectionOne-Class Classification	CodeCode Available	1
Learning and Evaluating Representations for Deep One-class Classification	Nov 4, 2020	Anomaly DetectionClassification	CodeCode Available	1
Learning Not to Reconstruct Anomalies	Oct 19, 2021	Anomaly DetectionOne-Class Classification	CodeCode Available	1
Meta Learning for Few-Shot One-class Classification	Sep 11, 2020	ClassificationGeneral Classification	CodeCode Available	1
MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection	Dec 9, 2020	Anomaly DetectionClassification	CodeCode Available	1
One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks	Feb 22, 2020	Anomaly DetectionGeneral Classification	CodeCode Available	1
One-Class Convolutional Neural Network	Jan 24, 2019	Anomaly DetectionGeneral Classification	CodeCode Available	1
PREGO: online mistake detection in PRocedural EGOcentric videos	Apr 2, 2024	Action RecognitionBenchmarking	CodeCode Available	1
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection	Nov 16, 2021	Action RecognitionAnomaly Detection	CodeCode Available	1

Title

Status

Hype

Few-Shot One-Class Classification via Meta-Learning

CodeCode Available

FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data

CodeCode Available

Learning and Evaluating Representations for Deep One-class Classification

CodeCode Available

Learning Not to Reconstruct Anomalies

CodeCode Available

Meta Learning for Few-Shot One-class Classification