CADet: Fully Self-Supervised Anomaly Detection With Contrastive Learning

by   Charles Guille-Escuret, et al.
Montréal Institute of Learning Algorithms

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the application of self-supervised contrastive learning to the simultaneous detection of two types of OOD samples: unseen classes and adversarial perturbations. Since in practice the distribution of such samples is not known in advance, we do not assume access to OOD examples. We show that similarity functions trained with contrastive learning can be leveraged with the maximum mean discrepancy (MMD) two-sample test to verify whether two independent sets of samples are drawn from the same distribution. Inspired by this approach, we introduce CADet (Contrastive Anomaly Detection), a method based on image augmentations to perform anomaly detection on single samples. CADet compares favorably to adversarial detection methods to detect adversarially perturbed samples on ImageNet. Simultaneously, it achieves comparable performance to unseen label detection methods on two challenging benchmarks: ImageNet-O and iNaturalist. CADet is fully self-supervised and requires neither labels for in-distribution samples nor access to OOD examples.


page 1

page 2

page 3

page 4


Contrastive Predictive Coding for Anomaly Detection

Reliable detection of anomalies is crucial when deploying machine learni...

Contrastive Training for Improved Out-of-Distribution Detection

Reliable detection of out-of-distribution (OOD) inputs is increasingly u...

Self-Supervised Anomaly Detection by Self-Distillation and Negative Sampling

Detecting whether examples belong to a given in-distribution or are Out-...

Self-Supervised Anomaly Detection of Rogue Soil Moisture Sensors

IoT data is a central element in the successful digital transformation o...

Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity

Every year, criminals launder billions of dollars acquired from serious ...

GCCAD: Graph Contrastive Coding for Anomaly Detection

Graph-based anomaly detection has been widely used for detecting malicio...

Safe Robot Navigation via Multi-Modal Anomaly Detection

Navigation in natural outdoor environments requires a robust and reliabl...

Please sign up or login with your details

Forgot password? Click here to reset