DeepAI
Log In Sign Up

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

07/25/2022
by   Adam Dziedzic, et al.
0

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. p-DkNN is scalable and leverages the composition of representations learned by hidden layers, which makes deep representation learning successful. Our theoretical analysis builds on Neyman-Pearson classification and connects it to recent advances in selective classification (reject option). We demonstrate advantageous trade-offs between abstaining from predicting on OOD inputs and maintaining high accuracy on in-distribution inputs. We find that p-DkNN forces adaptive attackers crafting adversarial examples, a form of worst-case OOD inputs, to introduce semantically meaningful changes to the inputs.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/26/2019

SelectiveNet: A Deep Neural Network with an Integrated Reject Option

We consider the problem of selective prediction (also known as reject op...
02/17/2019

Towards Improved Testing For Deep Learning

The growing use of deep neural networks in safety-critical applications ...
01/24/2022

What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction

Adversarial examples (AEs) pose severe threats to the applications of de...
11/30/2018

Ensemble Bayesian Decision Making with Redundant Deep Perceptual Control Policies

This work presents a novel ensemble of Bayesian Neural Networks (BNNs) f...
07/29/2020

Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers

Detecting anomalous inputs, such as adversarial and out-of-distribution ...
07/16/2020

Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data

Deep neural networks are known to be overconfident when applied to out-o...
05/06/2022

Norm-Scaling for Out-of-Distribution Detection

Out-of-Distribution (OoD) inputs are examples that do not belong to the ...