Fig.1

Concept

Out-of-distribution

Out-of-distribution (OOD) refers to any input a model encounters at inference time that differs meaningfully from the data distribution it was trained on. The complement is in-distribution: inputs drawn from the same distribution as the training set.

The rest of “Out-of-distribution” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

Out-of-distribution, explained · Fig. 1