$p$-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations

Understand

The lack of well-calibrated confidence estimates makes neural networks inadequate in safety-critical domains such as autonomous driving or healthcare.

• In these settings, having the ability to abstain from making a prediction on out-of-distribution (OOD) data can be as important as correctly classifying in-distribution data.
• We introduce $p$-DkNN, a novel inference procedure that takes a trained deep neural network and analyzes the similarity structures of its intermediate hidden representations to compute $p$-values associated with the end-to-end model prediction.
• The intuition is that statistical tests performed on latent representations can serve not only as a classifier, but also offer a statistically well-founded estimation of uncertainty.