arXiv (Cornell University) · 2022 · 11 citations · 0 references
ComputingComputer ScienceComputational GeometryComputer VisionMachine LearningDeep LearningDensity EstimationGenerative ModelingNeural NetworksPattern RecognitionRepresentation LearningDeep Learning DetectionDeep Learning-based DetectionLearned Feature RepresentationsOut-of-distribution DetectionProbabilistic Deep Learning
Reliable out-of-distribution (OOD) detection is fundamental to implementing safer modern machine learning (ML) systems. In this paper, we introduce Igeood, an effective method for detecting OOD samples. Igeood applies to any pre-trained neural network, works under various 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 can combine confidence scores from the logits outputs and the learned features of a deep neural network. Empirically, we show that Igeood outperforms competing state-of-the-art methods on a variety of network architectures and datasets.