Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Semi-supervised novelty detection using ensembles with regularized disagreement

About

Deep neural networks often predict samples with high confidence even when they come from unseen classes and should instead be flagged for expert evaluation. Current novelty detection algorithms cannot reliably identify such near OOD points unless they have access to labeled data that is similar to these novel samples. In this paper, we develop a new ensemble-based procedure for semi-supervised novelty detection (SSND) that successfully leverages a mixture of unlabeled ID and novel-class samples to achieve good detection performance. In particular, we show how to achieve disagreement only on OOD data using early stopping regularization. While we prove this fact for a simple data distribution, our extensive experiments suggest that it holds true for more complex scenarios: our approach significantly outperforms state-of-the-art SSND methods on standard image data sets (SVHN/CIFAR-10/CIFAR-100) and medical image data sets with only a negligible increase in computation cost.

Alexandru \c{T}ifrea, Eric Stavarache, Fanny Yang• 2020

Related benchmarks

TaskDatasetResultRank
Out-of-Distribution DetectionCIFAR-10 (ID) vs SVHN (OOD) (test)
AUROC100
79
Out-of-Distribution DetectionCIFAR10 (ID) vs SVHN (OOD)
AUROC100
37
OOD DetectionCIFAR10 (ID) vs CIFAR100 (OOD) (test)
AUROC0.95
36
Novelty DetectionCIFAR10 [0:4] (ID) vs [5:9] (OOD) (test)
AUROC89
10
Novelty DetectionCIFAR100 [0:49] (ID) vs [50:99] (OOD) (test)
AUROC0.81
10
Novelty DetectionCIFAR100 (ID) vs SVHN (OOD) (test)
AUROC1
10
Novelty DetectionSVHN [0:4] (ID) vs [5:9] (OOD) (test)
AUROC0.95
10
Novelty DetectionFashionMNIST [0,2,3,7,8] (ID) vs [1,4,5,6,9] (OOD) (unlabeled set)
AUROC94
10
Novelty DetectionSVHN (ID) vs CIFAR10 (OOD) (test)
AUROC100
10
Novelty DetectionFashionMNIST (ID) vs MNIST (OOD) (unlabeled set)
AUROC100
10
Showing 10 of 36 rows

Other info

Code

Follow for update