DeepAI AI Chat
Log In Sign Up

iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection

01/07/2022
by   Ramneet Kaur, et al.
University of Pennsylvania
SRI International
0

Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence on inputs outside their training distribution. The deployment of DNNs in safety-critical domains requires detection of out-of-distribution (OOD) data so that DNNs can abstain from making predictions on those. A number of methods have been recently developed for OOD detection, but there is still room for improvement. We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection. It relies on a novel base non-conformity measure and a new aggregation method, used in the inductive conformal anomaly detection framework, thereby guaranteeing a bounded false detection rate. We demonstrate the efficacy of iDECODe by experiments on image and audio datasets, obtaining state-of-the-art results. We also show that iDECODe can detect adversarial examples.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/13/2021

Detecting OODs as datapoints with High Uncertainty

Deep neural networks (DNNs) are known to produce incorrect predictions w...
02/25/2021

Statistical Testing for Efficient Out of Distribution Detection in Deep Neural Networks

Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn f...
12/05/2019

Why Should we Combine Training and Post-Training Methods for Out-of-Distribution Detection?

Deep neural networks are known to achieve superior results in classifica...
06/25/2020

The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches

Deep neural networks (DNNs) have become the de facto learning mechanism ...
02/13/2018

Learning Confidence for Out-of-Distribution Detection in Neural Networks

Modern neural networks are very powerful predictive models, but they are...
11/30/2022

Rethinking Out-of-Distribution Detection From a Human-Centric Perspective

Out-Of-Distribution (OOD) detection has received broad attention over th...