Out-of-Distribution Detection using Outlier Detection Methods

Out-of-distribution detection (OOD) deals with anomalous input to neural networks. In the past, specialized methods have been proposed to reject predictions on anomalous input. We use outlier detection algorithms to detect anomalous input as reliable as specialized methods from the field of OOD. No neural network adaptation is required; detection is based on the model's softmax score. Our approach works unsupervised with an Isolation Forest or with supervised classifiers such as a Gradient Boosting machine.