@InProceedings{FonsecaNegPerCouGui:2021:ToAuMa,
author = "Fonseca, Gabriel Barbosa da and Negrel, Romain and Perret,
Benjamin and Cousty, Jean and Guimar{\~a}es, Silvio Jamil
Ferzoli",
affiliation = "{Pontif{\'{\i}}cia Universidade Cat{\'o}lica de Minas Gerais }
and {ESIEE Paris } and LIGM, Universit{\'e} Gustave Eiffel,
CNRS, ESIEE Paris and LIGM, Universit{\'e} Gustave Eiffel,
CNRS, ESIEE Paris and {Pontif{\'{\i}}cia Universidade
Cat{\'o}lica de Minas Gerais}",
title = "New hierarchy-based segmentation layer: towards automatic marker
proposal",
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 = "interactive image segmentation, automatic marker proposal,
segmentation layer, deep learning.",
abstract = "Image segmentation is an ill-posed problem by definition, as it is
not always possible to automatically select which object appearing
in an image is the object of interest. To deal with this issue,
prior knowledge in the form of human-given markers can be included
in the segmentation pipeline. Even though user interaction can
drastically improve segmentation results, it is an expensive
resource, and finding ways to reduce human effort on an
interactive segmentation loop is of great interest. In this work,
we propose a new segmentation layer to be used with deep neural
networks, which allows us to create and train in an end-to-end
fashion a marker creation network. To train the network, we
propose a loss function composed of: a segmentation loss using the
proposed differentiable segmentation layer; and a set of
regularization functions that enforce the desired characteristics
on the produced markers. We showed that by using the proposed
layer and loss function, we can train the network to automatically
generate markers that recover a good segmentation and have
desirable shape characteristics. This behavior is observed on the
training dataset, as well as on four unseen datasets.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00055",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00055",
language = "en",
ibi = "8JMKD3MGPEW34M/45CS5L8",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CS5L8",
targetfile = "SIBGRAPI2021_learning_markers_CR2.pdf",
urlaccessdate = "2024, May 06"
}