Two Is Better Than One: Aligned Clusters Improve Anomaly Detection


Date

2024-12-14

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Anomaly detection focuses on identifying samples that deviate from the norm. When working with high-dimensional data such as images, a crucial requirement for detecting anomalous patterns is learning lower-dimensional representations that capture concepts of normality. Recent advances in self-supervised learning have shown great promise in this regard. However, many successful self-supervised anomaly detection methods assume prior knowledge about anomalies to create synthetic outliers during training. Yet, in real-world applications, we often do not know what to expect from unseen data, and we can solely leverage knowledge about normal data. In this work, we propose Con , which learns representations through context augmentations that model invariances of normal data while letting us observe samples from two distinct perspectives. At test time, representations of anomalies that do not adhere to these invariances deviate from the representation structure learned during training, allowing us to detect anomalies without relying on prior knowledge about them.

Publication status

published

Editor

Book title

NeurIPS 2024 Workshop: Self-Supervised Learning - Theory and Practice

Journal / series

Volume

Pages / Article No.

Publisher

OpenReview

Event

NeurIPS 2024 Workshop: Self-Supervised Learning - Theory and Practice

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09670 - Vogt, Julia / Vogt, Julia check_circle

Notes

Funding

Related publications and datasets