Logo image
Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders
Conference proceeding

Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders

Feiyang Cai, Ali Ozdagli, Nicholas Potteiger, Xenofon Koutsoukos and IEEE
2021 IEEE INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2021), pp.90-95
01-01-2021

Abstract

Computer Science Computer Science, Artificial Intelligence Computer Science, Hardware & Architecture Computer Science, Information Systems Computer Science, Interdisciplinary Applications Computer Science, Theory & Methods Science & Technology Technology
Machine learning components are used extensively to cope with various complex tasks in highly-uncertain environments. However, Out-Of-Distribution (OOD) data may lead to predictions with large errors and degrade performance considerably. This paper first introduces different types of OOD data and then presents an approach for OOD detection for classification problems efficiently. Our approach utilizes an Adversarial Autoencoder (AAE) for representing the training distribution and Inductive Conformal Anomaly Detection (ICAD) for online detecting OOD high-dimensional data. Experimental results using several datasets demonstrate that the approach can detect various types of OOD data with a small number of false alarms. Moreover, the execution time is very short, allowing for online detection.

Metrics

Details

Logo image