TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Classification-Based Anomaly Detection for General Data

Classification-Based Anomaly Detection for General Data

Liron Bergman, Yedid Hoshen

2020-05-05ICLR 2020 1Anomaly DetectionGeneral ClassificationClassification
PaperPDFCodeCode

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.

Results

TaskDatasetMetricValueModel
Anomaly DetectionAnomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102ROC-AUC92.8GOAD
Anomaly DetectionAnomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)ROC-AUC78.8GOAD
Anomaly DetectionUEA time-series datasetsAvg. ROC-AUC87.2GOAD
Anomaly DetectionUnlabeled CIFAR-10 vs CIFAR-100AUROC89.2GOAD
Anomaly DetectionAnomaly Detection on Unlabeled ImageNet-30 vs CUB-200ROC-AUC90.5GOAD
Anomaly DetectionOne-class CIFAR-10AUROC88.2GOAD

Related Papers

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems2025-07-213DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering2025-07-17A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys2025-07-17Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy2025-07-16Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation2025-07-16Safeguarding Federated Learning-based Road Condition Classification2025-07-16Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection2025-07-15