loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Mikhaël Presley Kibinda-Moukengue ; Alexandre Baussard and Pierre Beauseroy

Affiliation: Computer Science and Digital Society Laboratory (LIST3N), Université de Technologie de Troyes, Troyes, France

Keyword(s): Deep Neural Networks, Out-of-Distribution, Detection, Statistical Hypothesis Tests.

Abstract: Decision-making in a number of industries, including environmental management, transportation, and public health, is greatly aided by artificial intelligence systems. Nonetheless, to perform well, these systems requires to follow some usage conditions. For instance, the data fed into a classification neural network must come from the same distribution as the training data to maintain the performance measured during test. In practice, however, this condition is not always met and not so easy to guarantee. In particular, for image recognition, it’s possible to submit images that do not contain any learned classes and still receive a firm response from the network. This paper presents an approach to out-of-distribution observation detection applied to deep neural networks (DNNs) for image classification, called DNN Layers Features Reduction for Out-Of-Distribution Detection (DROOD). The principle of DROOD is to construct a decision statistic by successively synthesizing information from the features of all the intermediate layers of the classification network. The method is adaptable to any DNN architecture and experiments show results that outperform reference methods. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.23.59.191

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kibinda-Moukengue, M. P., Baussard, A. and Beauseroy, P. (2025). DNN Layers Features Reduction for Out-of-Distribution Detection. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-730-6; ISSN 2184-4313, SciTePress, pages 70-78. DOI: 10.5220/0013167400003905

@conference{icpram25,
author={Mikhaël Presley Kibinda{-}Moukengue and Alexandre Baussard and Pierre Beauseroy},
title={DNN Layers Features Reduction for Out-of-Distribution Detection},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2025},
pages={70-78},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013167400003905},
isbn={978-989-758-730-6},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - DNN Layers Features Reduction for Out-of-Distribution Detection
SN - 978-989-758-730-6
IS - 2184-4313
AU - Kibinda-Moukengue, M.
AU - Baussard, A.
AU - Beauseroy, P.
PY - 2025
SP - 70
EP - 78
DO - 10.5220/0013167400003905
PB - SciTePress