@InProceedings{MoraesEvanFernMart:2021:GeCoOu,
author = "Moraes, Rog{\'e}rio Ferreira de and Evangelista, Raphael dos S.
and Fernandes, Leandro A. F. and Mart{\'{\i}}, Luis",
affiliation = "Universidade Federal Fluminense (UFF), Niter{\'o}i, Brazil and
Universidade Federal Fluminense (UFF), Niter{\'o}i, Brazil and
Universidade Federal Fluminense (UFF), Niter{\'o}i, Brazil and
Inria Chile Research Center, Las Condes, Chile",
title = "GCOOD: A Generic Coupled Out-of-Distribution Detector for Robust
Classification",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "OOD, Voronoi diagrams.",
abstract = "Neural networks have achieved high degrees of accuracy in
classification tasks. However, when an out-of-distribution (OOD)
sample (\emph{i.e.,}~entries from unknown classes) is submitted
to the classification process, the result is the association of
the sample to one or more of the trained classes with different
degrees of confidence. If any of these confidence values are more
significant than the user-defined threshold, the network will
mislabel the sample, affecting the model credibility. The
definition of the acceptance threshold itself is a sensitive issue
in the face of the classifier's overconfidence. This paper
presents the Generic Coupled OOD Detector (GCOOD), a novel
Convolutional Neural Network (CNN) tailored to detect whether an
entry submitted to a trained classification model is an OOD sample
for that model. From the analysis of the Softmax output of any
classifier, our approach can indicate whether the resulting
classification should be considered or not as a sample of some of
the trained classes. To train our CNN, we had to develop a novel
training strategy based on Voronoi diagrams of the location of
representative entries in the latent space of the classification
model and graph coloring. We evaluated our approach using ResNet,
VGG, DenseNet, and SqueezeNet classifiers with images from the
CIFAR-10 dataset.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00062",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00062",
language = "en",
ibi = "8JMKD3MGPEW34M/45EACT2",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45EACT2",
targetfile = "2021___Moraes_et_al____SIBGRAPI.pdf",
urlaccessdate = "2024, May 06"
}