Classification-Based Anomaly Detection for General Data
Liron Bergman, Yedid Hoshen
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/xuhongzuo/DeepODpytorch★ 565
- github.com/lironber/GOADpytorch★ 90
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 | GOAD | ROC-AUC | 92.8 | — | Unverified |
| Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) | GOAD | ROC-AUC | 78.8 | — | Unverified |
| Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200 | GOAD | ROC-AUC | 90.5 | — | Unverified |
| One-class CIFAR-10 | GOAD | AUROC | 88.2 | — | Unverified |
| UEA time-series datasets | GOAD | Avg. ROC-AUC | 87.2 | — | Unverified |
| Unlabeled CIFAR-10 vs CIFAR-100 | GOAD | AUROC | 89.2 | — | Unverified |