Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities

by   Julian Bitterwolf, et al.

It is an important problem in trustworthy machine learning to recognize out-of-distribution (OOD) inputs which are inputs unrelated to the in-distribution task. Many out-of-distribution detection methods have been suggested in recent years. The goal of this paper is to recognize common objectives as well as to identify the implicit scoring functions of different OOD detection methods. We focus on the sub-class of methods that use surrogate OOD data during training in order to learn an OOD detection score that generalizes to new unseen out-distributions at test time. We show that binary discrimination between in- and (different) out-distributions is equivalent to several distinct formulations of the OOD detection problem. When trained in a shared fashion with a standard classifier, this binary discriminator reaches an OOD detection performance similar to that of Outlier Exposure. Moreover, we show that the confidence loss which is used by Outlier Exposure has an implicit scoring function which differs in a non-trivial fashion from the theoretically optimal scoring function in the case where training and test out-distribution are the same, which again is similar to the one used when training an Energy-Based OOD detector or when adding a background class. In practice, when trained in exactly the same way, all these methods perform similarly.


page 33

page 34


Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?

Supervised classification methods often assume the train and test data d...

Out-of-distribution Detection with Implicit Outlier Transformation

Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection...

Energy-based Out-of-distribution Detection

Determining whether inputs are out-of-distribution (OOD) is an essential...

Deep Anomaly Detection with Outlier Exposure

It is important to detect and handle anomalous inputs when deploying mac...

Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

Methods which utilize the outputs or feature representations of predicti...

Kernel-based Outlier Detection using the Inverse Christoffel Function

Outlier detection methods have become increasingly relevant in recent ye...

Machine learning based forecasting of significant daily returns in foreign exchange markets

Asset value forecasting has always attracted an enormous amount of inter...

Please sign up or login with your details

Forgot password? Click here to reset