Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-Out Classifiers

Abstract

As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers. We train each classifier in a self-supervised manner by leaving out a random subset of training data as OOD data and the rest as in-distribution (ID) data. We propose a novel margin-based loss over the softmax output which seeks to maintain at least a margin m between the average entropy of the OOD and in-distribution samples. In conjunction with the standard cross-entropy loss, we minimize the novel loss to train an ensemble of classifiers. We also propose a novel method to combine the outputs of the ensemble of classifiers to obtain OOD detection score and class prediction. Overall, our method convincingly outperforms Hendrycks et al. [7] and the current state-of-the-art ODIN [13] on several OOD detection benchmarks.

Cite

Text

Vyas et al. "Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-Out Classifiers." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01237-3_34

Markdown

[Vyas et al. "Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-Out Classifiers." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/vyas2018eccv-outofdistribution/) doi:10.1007/978-3-030-01237-3_34

BibTeX

@inproceedings{vyas2018eccv-outofdistribution,
  title     = {{Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-Out Classifiers}},
  author    = {Vyas, Apoorv and Jammalamadaka, Nataraj and Zhu, Xia and Das, Dipankar and Kaul, Bharat and Willke, Theodore L.},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01237-3_34},
  url       = {https://mlanthology.org/eccv/2018/vyas2018eccv-outofdistribution/}
}