Conference paper Open Access

Learning Short-Cut Connections for Object Counting

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


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3813490</identifier>
  <creators>
    <creator>
      <creatorName>Daniel Oñoro-Rubio</creatorName>
      <affiliation>NEC Lab Europe</affiliation>
    </creator>
    <creator>
      <creatorName>Mathias Niepert</creatorName>
      <affiliation>NEC Lab Europe</affiliation>
    </creator>
    <creator>
      <creatorName>Roberto J. López-Sastre</creatorName>
      <affiliation>University de Alcalá de Henares</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Learning Short-Cut Connections for Object Counting</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <dates>
    <date dateType="Issued">2018-11-15</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3813490</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3813489</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/5gcity</relatedIdentifier>
  </relatedIdentifiers>
  <version>v.2</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/761508/">761508</awardNumber>
      <awardTitle>5GCITY</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
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