SSD: A Unified Framework for Self-Supervised Outlier Detection

by   Vikash Sehwag, et al.

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


page 1

page 2

page 3

page 4


Self-EMD: Self-Supervised Object Detection without ImageNet

In this paper, we propose a novel self-supervised representation learnin...

Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection

Deep neural networks have found widespread adoption in solving complex t...

Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?

Unsupervised outlier detection, which predicts if a test sample is an ou...

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

Facial landmark detection aims to localize the anatomically defined poin...

OpenMix: Exploring Outlier Samples for Misclassification Detection

Reliable confidence estimation for deep neural classifiers is a challeng...

Constrained self-supervised method with temporal ensembling for fiber bundle detection on anatomic tracing data

Anatomic tracing data provides detailed information on brain circuitry e...

Supervision by Registration and Triangulation for Landmark Detection

We present Supervision by Registration and Triangulation (SRT), an unsup...

Please sign up or login with your details

Forgot password? Click here to reset