Skip to Main content Skip to Navigation
Conference papers

Igeood: An Information Geometry Approach to Out-of-Distribution Detection

Abstract : 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.
Complete list of metadata
Contributor : Eduardo Dadalto Camara Gomes Connect in order to contact the contributor
Submitted on : Wednesday, March 16, 2022 - 5:45:27 PM
Last modification on : Tuesday, May 17, 2022 - 3:00:35 AM

Links full text


  • HAL Id : hal-03611011, version 1
  • ARXIV : 2203.07798


Eduardo Dadalto Câmara Gomes, Florence Alberge, Pierre Duhamel, Pablo Piantanida. Igeood: An Information Geometry Approach to Out-of-Distribution Detection. International Conference on Learning Representations, Apr 2022, Virtual, France. ⟨hal-03611011⟩



Record views