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

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.