Timezone: »

 
Poster
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
Charles Guille-Escuret · Pau Rodriguez · David Vazquez · Ioannis Mitliagkas · Joao Monteiro

Wed Dec 13 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #803
in Poster Session 3 »

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of OOD samples: unseen classes and adversarial perturbations. First, we pair self-supervised contrastive learning with the maximum mean discrepancy (MMD) two-sample test. This approach enables us to robustly test whether two independent sets of samples originate from the same distribution, and we demonstrate its effectiveness by discriminating between CIFAR-10 and CIFAR-10.1 with higher confidence than previous work. Motivated by this success, we introduce CADet (Contrastive Anomaly Detection), a novel method for OOD detection of single samples. CADet draws inspiration from MMD, but leverages the similarity between contrastive transformations of a same sample. CADet outperforms existing adversarial detection methods in identifying adversarially perturbed samples on ImageNet and achieves comparable performance to unseen label detection methods on two challenging benchmarks: ImageNet-O and iNaturalist. Significantly, CADet is fully self-supervised and requires neither labels for in-distribution samples nor access to OOD examples.

Author Information

Charles Guille-Escuret (Mila)
Pau Rodriguez (Apple)
David Vazquez (ServiceNow)
Ioannis Mitliagkas (University of Montreal)
Joao Monteiro (ServiceNow)

More from the Same Authors