POEM: Out-of-Distribution Detection with Posterior Sampling

Yifei Ming, Ying Fan, Yixuan Li
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:15650-15665, 2022.

Abstract

Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also known as outlier exposure) has shown promising performance. As the sample space for potential OOD data can be prohibitively large, sampling informative outliers is essential. In this work, we propose a novel posterior sampling based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection. We show that POEM establishes state-of-the-art performance on common benchmarks. Compared to the current best method that uses a greedy sampling strategy, POEM improves the relative performance by 42.0% and 24.2% (FPR95) on CIFAR-10 and CIFAR-100, respectively. We further provide theoretical insights on the effectiveness of POEM for OOD detection.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-ming22a, title = {{POEM}: Out-of-Distribution Detection with Posterior Sampling}, author = {Ming, Yifei and Fan, Ying and Li, Yixuan}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {15650--15665}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/ming22a/ming22a.pdf}, url = {https://proceedings.mlr.press/v162/ming22a.html}, abstract = {Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also known as outlier exposure) has shown promising performance. As the sample space for potential OOD data can be prohibitively large, sampling informative outliers is essential. In this work, we propose a novel posterior sampling based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection. We show that POEM establishes state-of-the-art performance on common benchmarks. Compared to the current best method that uses a greedy sampling strategy, POEM improves the relative performance by 42.0% and 24.2% (FPR95) on CIFAR-10 and CIFAR-100, respectively. We further provide theoretical insights on the effectiveness of POEM for OOD detection.} }
Endnote
%0 Conference Paper %T POEM: Out-of-Distribution Detection with Posterior Sampling %A Yifei Ming %A Ying Fan %A Yixuan Li %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-ming22a %I PMLR %P 15650--15665 %U https://proceedings.mlr.press/v162/ming22a.html %V 162 %X Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also known as outlier exposure) has shown promising performance. As the sample space for potential OOD data can be prohibitively large, sampling informative outliers is essential. In this work, we propose a novel posterior sampling based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection. We show that POEM establishes state-of-the-art performance on common benchmarks. Compared to the current best method that uses a greedy sampling strategy, POEM improves the relative performance by 42.0% and 24.2% (FPR95) on CIFAR-10 and CIFAR-100, respectively. We further provide theoretical insights on the effectiveness of POEM for OOD detection.
APA
Ming, Y., Fan, Y. & Li, Y.. (2022). POEM: Out-of-Distribution Detection with Posterior Sampling. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:15650-15665 Available from https://proceedings.mlr.press/v162/ming22a.html.

Related Material