Learning to Augment Distributions for Out-of-distribution Detection

Qizhou Wang, Zhen Fang, Yonggang Zhang, Feng Liu, Yixuan Li, Bo Han*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

5 Citations (Scopus)

Abstract

Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may still fail in the open world, owing to the lack of knowledge about unseen OOD data in advance. Although one can access auxiliary OOD data (distinct from unseen ones) for model training, it remains to analyze how such auxiliary data will work in the open world. To this end, we delve into such a problem from a learning theory perspective, finding that the distribution discrepancy between the auxiliary and the unseen real OOD data is the key to affecting the open-world detection performance. Accordingly, we propose Distributional-Augmented OOD Learning (DAL), alleviating the OOD distribution discrepancy by crafting an OOD distribution set that contains all distributions in a Wasserstein ball centered on the auxiliary OOD distribution. We justify that the predictor trained over the worst OOD data in the ball can shrink the OOD distribution discrepancy, thus improving the open-world detection performance given only the auxiliary OOD data. We conduct extensive evaluations across representative OOD detection setups, demonstrating the superiority of our DAL over its advanced counterparts. The code is publicly available at: https://github.com/tmlr-group/DAL.
Original languageEnglish
Title of host publication37th Conference on Neural Information Processing Systems, NeurIPS 2023
EditorsA. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, S. Levine
PublisherNeural Information Processing Systems Foundation
Number of pages13
Publication statusPublished - 14 Dec 2023
Event37th Conference on Neural Information Processing Systems, NeurIPS 2023 - Ernest N. Morial Convention Center, New Orleans, United States
Duration: 10 Dec 202316 Dec 2023
https://proceedings.neurips.cc/paper_files/paper/2023 (conference paper search)
https://openreview.net/group?id=NeurIPS.cc/2023/Conference#tab-accept-oral (conference paper search)
https://neurips.cc/Conferences/2023 (conference website)

Publication series

NameAdvances in Neural Information Processing Systems
Volume36
ISSN (Print)1049-5258
NameNeurIPS Proceedings

Conference

Conference37th Conference on Neural Information Processing Systems, NeurIPS 2023
Country/TerritoryUnited States
CityNew Orleans
Period10/12/2316/12/23
Internet address

Fingerprint

Dive into the research topics of 'Learning to Augment Distributions for Out-of-distribution Detection'. Together they form a unique fingerprint.

Cite this