Semi-supervised novelty detection using ensembles with regularized disagreement

December 10, 2020 Β· Declared Dead Β· πŸ› Conference on Uncertainty in Artificial Intelligence

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Alexandru Ε’ifrea, Eric Stavarache, Fanny Yang arXiv ID 2012.05825 Category cs.LG: Machine Learning Citations 7 Venue Conference on Uncertainty in Artificial Intelligence Last Checked 3 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Machine Learning

Died the same way β€” πŸ‘» Ghosted