Skip to Main content Skip to Navigation
New interface
Conference poster

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

Abstract : ▶ In this paper, we introduce Igeood, an effective method for detecting Out-of-Distribution (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.
Complete list of metadata
Contributor : Eduardo Dadalto Camara Gomes Connect in order to contact the contributor
Submitted on : Friday, April 22, 2022 - 10:43:12 AM
Last modification on : Sunday, June 26, 2022 - 4:34:02 AM
Long-term archiving on: : Saturday, July 23, 2022 - 6:22:38 PM


Files produced by the author(s)


  • HAL Id : hal-03649034, version 1


Eduardo Dadalto Câmara Gomes, Florence Alberge, Pierre Duhamel, Pablo Piantanida. Igeood: An Information Geometry Approach to Out-of-Distribution Detection. NeurIPS DistShift Workshop 2021, Dec 2021, Virtual, France. ⟨hal-03649034⟩



Record views


Files downloads