Out-of-Distribution Detection Using Outlier Detection Methods
This provides a simpler, unsupervised approach for detecting anomalous inputs in neural networks, though it appears incremental as it adapts existing outlier detection techniques.
The paper tackles out-of-distribution detection in neural networks by applying outlier detection methods to softmax scores, achieving reliability comparable to specialized OOD methods without requiring network adaptation.
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. Similarly, it was shown that feature extraction models in combination with outlier detection algorithms are well suited to detect 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 using an Isolation Forest and can be further improved by using a supervised learning method such as Gradient Boosting.