SSD: A Unified Framework for Self-Supervised Outlier Detection

ICLR 2021  ·  Vikash Sehwag, Mung Chiang, Prateek Mittal ·

We ask the following question: what training information is required to design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting samples that lie far away from the training distribution? Since unlabeled data is easily accessible for many applications, the most compelling approach is to develop detectors based on only unlabeled in-distribution data. However, we observe that most existing detectors based on unlabeled data perform poorly, often equivalent to a random prediction. In contrast, existing state-of-the-art OOD detectors achieve impressive performance but require access to fine-grained data labels for supervised training. We propose SSD, an outlier detector based on only unlabeled in-distribution data. We use self-supervised representation learning followed by a Mahalanobis distance based detection in the feature space. We demonstrate that SSD outperforms most existing detectors based on unlabeled data by a large margin. Additionally, SSD even achieves performance on par, and sometimes even better, with supervised training based detectors. Finally, we expand our detection framework with two key extensions. First, we formulate few-shot OOD detection, in which the detector has access to only one to five samples from each class of the targeted OOD dataset. Second, we extend our framework to incorporate training data labels, if available. We find that our novel detection framework based on SSD displays enhanced performance with these extensions, and achieves state-of-the-art performance. Our code is publicly available at https://github.com/inspire-group/SSD.

PDF Abstract ICLR 2021 PDF ICLR 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) SSD ROC-AUC 96.5 # 2
Network ResNet-34 # 1
Out-of-Distribution Detection ImageNet-1k vs Textures SSD FPR95 57.2 # 20
AUROC 85.4 # 21
Anomaly Detection One-class CIFAR-10 SSD AUROC 90.0 # 18
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 SSD AUROC 89.6 # 6
Network ResNet-18 # 1

Methods