loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Daniel Lehmann and Marc Ebner

Affiliation: Institut für Mathematik und Informatik, Universität Greifswald, Walther-Rathenau-Straße 47, 17489 Greifswald, Germany

Keyword(s): CNN, Out-of-Distribution Detection, Clustering.

Abstract: A convolutional neural network model is able to achieve high classification performance on test samples at inference, as long as those samples are drawn from the same distribution as the samples used for model training. However, if a test sample is drawn from a different distribution, the performance of the model decreases drastically. Such a sample is typically referred to as an out-of-distribution (OOD) sample. Papernot and McDaniel (2018) propose a method, called Deep k-Nearest Neighbors (DkNN), to detect OOD samples by a credibility score. However, DkNN are slow at inference as they are based on a kNN search. To address this problem, we propose a detection method that uses clustering instead of a kNN search. We conducted experiments with different types of OOD samples for models trained on either MNIST, SVHN, or CIFAR10. Our experiments show that our method is significantly faster than DkNN, while achieving similar performance.

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 3.239.91.5

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:
Lehmann, D. and Ebner, M. (2022). Calculating the Credibility of Test Samples at Inference by a Layer-wise Activation Cluster Analysis of Convolutional Neural Networks. In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - DeLTA; ISBN 978-989-758-584-5; ISSN 2184-9277, SciTePress, pages 34-43. DOI: 10.5220/0011274000003277

@conference{delta22,
author={Daniel Lehmann. and Marc Ebner.},
title={Calculating the Credibility of Test Samples at Inference by a Layer-wise Activation Cluster Analysis of Convolutional Neural Networks},
booktitle={Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - DeLTA},
year={2022},
pages={34-43},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011274000003277},
isbn={978-989-758-584-5},
issn={2184-9277},
}

TY - CONF

JO - Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - DeLTA
TI - Calculating the Credibility of Test Samples at Inference by a Layer-wise Activation Cluster Analysis of Convolutional Neural Networks
SN - 978-989-758-584-5
IS - 2184-9277
AU - Lehmann, D.
AU - Ebner, M.
PY - 2022
SP - 34
EP - 43
DO - 10.5220/0011274000003277
PB - SciTePress