Classification-Based Anomaly Detection for General Data

Abstract

Anomaly detection, finding patterns that substantially deviate from those seen previously, is one of the fundamental problems of artificial intelligence. Recently, classification-based methods were shown to achieve superior results on this task. In this work, we present a unifying view and propose an open-set method, GOAD, to relax current generalization assumptions. Furthermore, we extend the applicability of transformation-based methods to non-image data using random affine transformations. Our method is shown to obtain state-of-the-art accuracy and is applicable to broad data types. The strong performance of our method is extensively validated on multiple datasets from different domains.

ICLR'20

References in corpus (2)

• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Deep Anomaly Detection with Outlier Exposure

Cited by in corpus (39)

• Sub-Image Anomaly Detection with Deep Pyramid Correspondences
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
• Explainable Deep One-Class Classification
• Learning and Evaluating Representations for Deep One-class Classification
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• Contrastive Out-of-Distribution Detection for Pretrained Transformers
• Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation
• SSD: A Unified Framework for Self-Supervised Outlier Detection
• Explainable Deep Few-shot Anomaly Detection with Deviation Networks
• Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
• Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
• Neural Transformation Learning for Deep Anomaly Detection Beyond Images
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Anomaly Detection with Tensor Networks
• Rethinking Assumptions in Deep Anomaly Detection
• Anomaly Detection with Domain Adaptation
• Further Analysis of Outlier Detection with Deep Generative Models
• Detecting OODs as datapoints with High Uncertainty
• DROCC: Deep Robust One-Class Classification
• Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
• Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization
• Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images
• Discriminative-Generative Representation Learning for One-Class Anomaly Detection
• SLA${}^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
• Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images
• Multi-view Deep One-class Classification: A Systematic Exploration
• Deep Anomaly Detection by Residual Adaptation
• Shifting Transformation Learning for Out-of-Distribution Detection
• Enhancing Unsupervised Anomaly Detection with Score-Guided Network
• Test Sample Accuracy Scales with Training Sample Density in Neural Networks
• OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary
• Learning Augmentation Distributions using Transformed Risk Minimization
• A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it
• Unsupervised Learning of Multi-level Structures for Anomaly Detection
• Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection
• Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection
• INN: A Method Identifying Clean-annotated Samples via Consistency Effect in Deep Neural Networks
• Multi-Class Anomaly Detection