Skip to Main content Skip to Navigation
Conference papers

Addressing Failure Prediction by Learning Model Confidence

Abstract : Assessing reliably the confidence of a deep neural network and predicting its failures is of primary importance for the practical deployment of these models. In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP). We show how using the TCP is more suited than relying on the classic Maximum Class Probability (MCP). We provide in addition theoretical guarantees for TCP in the context of failure prediction. Since the true class is by essence unknown at test time, we propose to learn TCP criterion on the training set, introducing a specific learning scheme adapted to this context. Extensive experiments are conducted for validating the relevance of the proposed approach. We study various network architectures, small and large scale datasets for image classification and semantic segmentation. We show that our approach consistently outperforms several strong methods, from MCP to Bayesian uncertainty, as well as recent approaches specifically designed for failure prediction.
Complete list of metadata

Cited literature [45 references]  Display  Hide  Download
Contributor : Charles Corbière Connect in order to contact the contributor
Submitted on : Thursday, February 6, 2020 - 5:13:40 PM
Last modification on : Friday, August 5, 2022 - 2:54:00 PM
Long-term archiving on: : Thursday, May 7, 2020 - 4:07:02 PM


Files produced by the author(s)


  • HAL Id : hal-02469747, version 1
  • ARXIV : 1910.04851


Charles Corbière, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, Patrick Pérez. Addressing Failure Prediction by Learning Model Confidence. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Dec 2019, Vancouver, Canada. pp.2898-2909. ⟨hal-02469747⟩



Record views


Files downloads