English

Out-of-distribution Detection in Classifiers via Generation

Machine Learning 2019-10-11 v1 Machine Learning

Abstract

By design, discriminatively trained neural network classifiers produce reliable predictions only for in-distribution samples. For their real-world deployments, detecting out-of-distribution (OOD) samples is essential. Assuming OOD to be outside the closed boundary of in-distribution, typical neural classifiers do not contain the knowledge of this boundary for OOD detection during inference. There have been recent approaches to instill this knowledge in classifiers by explicitly training the classifier with OOD samples close to the in-distribution boundary. However, these generated samples fail to cover the entire in-distribution boundary effectively, thereby resulting in a sub-optimal OOD detector. In this paper, we analyze the feasibility of such approaches by investigating the complexity of producing such "effective" OOD samples. We also propose a novel algorithm to generate such samples using a manifold learning network (e.g., variational autoencoder) and then train an n+1 classifier for OOD detection, where the n+1thn+1^{th} class represents the OOD samples. We compare our approach against several recent classifier-based OOD detectors on MNIST and Fashion-MNIST datasets. Overall the proposed approach consistently performs better than the others.

Keywords

Cite

@article{arxiv.1910.04241,
  title  = {Out-of-distribution Detection in Classifiers via Generation},
  author = {Sachin Vernekar and Ashish Gaurav and Vahdat Abdelzad and Taylor Denouden and Rick Salay and Krzysztof Czarnecki},
  journal= {arXiv preprint arXiv:1910.04241},
  year   = {2019}
}

Comments

NeurIPS 2019, Safety and Robustness in Decision Making Workshop

R2 v1 2026-06-23T11:39:09.810Z