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

Eduardo Dadalto Câmara Gomes (1) , Florence Alberge (1) , Pierre Duhamel (1) , Pablo Piantanida (1)

1 L2S - Laboratoire des signaux et systèmes

▶ 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.

Domaines: Machine Learning [stat.ML]; Apprentissage [cs.LG]

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⟩