Conference paper Open Access

Learning Short-Cut Connections for Object Counting

Daniel Oñoro-Rubio; Mathias Niepert; Roberto J. López-Sastre


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">akh</subfield>
  </datafield>
  <controlfield tag="005">20200511202033.0</controlfield>
  <controlfield tag="001">3813490</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="a">BMBC 2018</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">NEC Lab Europe</subfield>
    <subfield code="a">Mathias Niepert</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University de Alcalá de Henares</subfield>
    <subfield code="a">Roberto J. López-Sastre</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1887158</subfield>
    <subfield code="z">md5:9974e8667992b03179bfee5dfeb4bb28</subfield>
    <subfield code="u">https://zenodo.org/record/3813490/files/Onoro-Rubio_Learning Short-Cut Connections for Object.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-11-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-5gcity</subfield>
    <subfield code="o">oai:zenodo.org:3813490</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">NEC Lab Europe</subfield>
    <subfield code="a">Daniel Oñoro-Rubio</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Learning Short-Cut Connections for Object Counting</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-5gcity</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">761508</subfield>
    <subfield code="a">5GCITY</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Object counting is an important task in computer vision due to its growing demand in applications such as traffic monitoring or surveillance. In this paper, we consider object counting as a learning problem of a joint feature extraction and pixel-wise object density estimation with Convolutional-Deconvolutional networks. We introduce a novel counting model, named Gated U-Net (GU-Net). Specifically, we propose to enrich the U-Net architecture with the concept of learnable short-cut connections. Standard short-cut connections are connections between layers in deep neural networks which skip at least one intermediate layer. Instead of simply setting short-cut connections, we propose to learn these connections from data. Therefore, our short-cuts can work as gating units, which optimize the flow of information between convolutional and deconvolutional layers in the U-Net architecture. We evaluate the introduced GU-Net architecture on three commonly used benchmark data sets for object counting. GU-Nets consistently outperform the base U-Net architecture, and achieve state-of-the-art performance.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3813489</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3813490</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
13
11
views
downloads
All versions This version
Views 1313
Downloads 1111
Data volume 20.8 MB20.8 MB
Unique views 1212
Unique downloads 1010

Share

Cite as