Semi-supervised novelty detection using ensembles with regularized disagreement

10 Dec 2020  ·  Alexandru Ţifrea, Eric Stavarache, Fanny Yang ·

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Out-of-Distribution Detection CIFAR-100 vs CIFAR-10 ERD (ResNet18) AUROC 94.3 # 8
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 ERD (ResNet18) AUROC 95.1 # 6
Out-of-Distribution Detection CIFAR-10 vs CIFAR-10.1 ERD (ResNet18) AUROC 91.4 # 1

Methods


No methods listed for this paper. Add relevant methods here