<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01412086v3</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-21T07:03:41+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Benchmarking losses for deep learning laxness detection</title>
            <author role="aut">
              <persName>
                <forename type="first">Adrien</forename>
                <surname>Chan-Hon-Tong</surname>
              </persName>
              <email type="md5">3b0ebf628c4a95cbd2d53edfb91d5cca</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">967233</idno>
              <idno type="halauthorid" notation="string">609634-967233</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7333-2765</idno>
              <idno type="IDREF">https://www.idref.fr/181792427</idno>
              <idno type="VIAF">https://viaf.org/viaf/311843416</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=tDnr7esAAAAJ</idno>
              <affiliation ref="#struct-252027"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Adrien</forename>
                <surname>Chan-Hon-Tong</surname>
              </persName>
              <email type="md5">3b0ebf628c4a95cbd2d53edfb91d5cca</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2016-12-07 22:34:50</date>
            </edition>
            <edition n="v2">
              <date type="whenSubmitted">2017-07-17 22:19:44</date>
            </edition>
            <edition n="v3" type="current">
              <date type="whenSubmitted">2017-07-31 14:30:40</date>
              <date type="whenModified">2024-05-30 15:07:05</date>
              <date type="whenReleased">2017-07-31 15:15:13</date>
              <date type="whenProduced">2017-07-31</date>
              <date type="whenEndEmbargoed">2017-07-31</date>
              <ref type="file" target="https://hal.science/hal-01412086v3/document">
                <date notBefore="2017-07-31"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01412086v3/file/raw.pdf" id="file-1570687-1623629">
                <date notBefore="2017-07-31"/>
              </ref>
            </edition>
            <edition n="v4">
              <date type="whenSubmitted">2017-10-18 16:04:16</date>
            </edition>
            <edition n="v5">
              <date type="whenSubmitted">2017-12-14 14:06:22</date>
            </edition>
            <edition n="v6">
              <date type="whenSubmitted">2017-12-15 15:25:10</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="172103">
                <persName>
                  <forename>Adrien</forename>
                  <surname>Chan-Hon-Tong</surname>
                </persName>
                <email type="md5">3b0ebf628c4a95cbd2d53edfb91d5cca</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01412086</idno>
            <idno type="halUri">https://hal.science/hal-01412086</idno>
            <idno type="halBibtex">chanhontong:hal-01412086</idno>
            <idno type="halRefHtml">2017</idno>
            <idno type="halRef">2017</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1570687-1623629"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Benchmarking losses for deep learning laxness detection</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Adrien</forename>
                    <surname>Chan-Hon-Tong</surname>
                  </persName>
                  <email type="md5">3b0ebf628c4a95cbd2d53edfb91d5cca</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">967233</idno>
                  <idno type="halauthorid" notation="string">609634-967233</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7333-2765</idno>
                  <idno type="IDREF">https://www.idref.fr/181792427</idno>
                  <idno type="VIAF">https://viaf.org/viaf/311843416</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=tDnr7esAAAAJ</idno>
                  <affiliation ref="#struct-252027"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ti">Computer Science [cs]/Image Processing [eess.IV]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>In object detection, classical rule for accepting a match between a ground truth area and a detection is a 0.5 jacard ratio. But does user care about this ? Especially, can this rule be well handled by deep network training ? And if no, may user accept some relaxation of the problem if it can help the training ?In this paper, we benchmark several strategies to perform object detection with end to end deep network when metric is relaxed.Our preliminary results on different public datasets show that under this relaxations, some strategies are very facilitative to train the network outperforming the same network learned with classical strategies.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-252027" status="OLD">
          <orgName>ONERA - The French Aerospace Lab [Palaiseau]</orgName>
          <date type="end">2018-03-18</date>
          <desc>
            <address>
              <addrLine>F-91761 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.onera.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300024" type="direct"/>
            <relation active="#struct-562112" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300024" status="VALID">
          <idno type="ROR">https://ror.org/005y2ap84</idno>
          <orgName>ONERA</orgName>
          <desc>
            <address>
              <addrLine>Office National d’Études et de Recherches Aéronautiques29, avenue de la Division Leclerc - BP 72 - 92322 CHATILLON CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.onera.fr/fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-562112" status="OLD">
          <orgName>Université Paris Saclay (COmUE)</orgName>
          <desc>
            <address>
              <addrLine>Espace Technologique, Bât. Discovery - RD 128 - 2è ététage, 91190 Saint-Aubin</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>