Keywords: out-of-distribution detection, anomaly detection, distribution drift, deep learning
TL;DR: We propose a flexible and effective out-of-distribution detection method by building on the Fisher-Rao distance between probability distributions.
Abstract: Reliable out-of-distribution (OOD) detection is a fundamental step towards a safer implementation of modern machine learning (ML) systems under distribution shift. In this paper, we introduce Igeood, an effective method for detecting OOD samples. Igeood applies to any pre-trained neural network, works under different degrees of access to the ML model, does not require OOD samples or assumptions on the OOD data, but can also benefit (if available) from OOD samples. By building on the geodesic (Fisher-Rao) distance between the underlying data distributions, our discriminator combines confidence scores from the logits outputs and the learned features of a deep neural network. Empirically, we show that Igeood is competitive and often outperforms state-of-the-art methods by a large margin on a variety of networks architectures and datasets.