Out-of-distribution detection using multiple semantic label representations

Gabi Shalev, Yossi Adi, Joseph Keshet

Research output: Contribution to journalConference articlepeer-review

44 Scopus citations

Abstract

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how a network will act when it is fed with an out-of-distribution example. In this work, we consider the problem of out-of-distribution detection in neural networks. We propose to use multiple semantic dense representations instead of sparse representation as the target label. Specifically, we propose to use several word representations obtained from different corpora or architectures as target labels. We evaluated the proposed model on computer vision, and speech commands detection tasks and compared it to previous methods. Results suggest that our method compares favorably with previous work. Besides, we present the efficiency of our approach for detecting wrongly classified and adversarial examples.

Original languageAmerican English
Pages (from-to)7375-7385
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2018-December
StatePublished - 2018
Externally publishedYes
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2 Dec 20188 Dec 2018

Bibliographical note

Publisher Copyright:
© 2018 Curran Associates Inc.All rights reserved.

Fingerprint

Dive into the research topics of 'Out-of-distribution detection using multiple semantic label representations'. Together they form a unique fingerprint.

Cite this