Poster De Conférence Année : 2021

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

Résumé

▶ 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.

Fichier principal
Vignette du fichier
Poster__NeurIPS_DistShift_2021___Igeood.pdf (1.25 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03649034 , version 1 (22-04-2022)

Licence

Identifiants

  • HAL Id : hal-03649034 , version 1

Citer

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⟩
144 Consultations
188 Téléchargements

Partager

  • More