Igeood: An Information Geometry Approach to Out-of-Distribution Detection - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (1) , (1)
1

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.

Dates and versions

hal-03611011 , version 1 (16-03-2022)

Identifiers

Cite

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⟩
41 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More