<?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-04910119</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="2026-05-17T00:46:09+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">MeSAM: Multiscale Enhanced Segment Anything Model for Optical Remote Sensing Images</title>
            <author role="aut">
              <persName>
                <forename type="first">Xichuan</forename>
                <surname>Zhou</surname>
              </persName>
              <idno type="idhal" notation="numeric">1496384</idno>
              <idno type="halauthorid" notation="string">3387107-1496384</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3304-3045</idno>
              <affiliation ref="#struct-237002"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Fu</forename>
                <surname>Liang</surname>
              </persName>
              <idno type="idhal" notation="numeric">1496385</idno>
              <idno type="halauthorid" notation="string">3387108-1496385</idno>
              <idno type="ORCID">https://orcid.org/0009-0008-1723-4651</idno>
              <affiliation ref="#struct-237002"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Lihui</forename>
                <surname>Chen</surname>
              </persName>
              <idno type="idhal" notation="numeric">1213555</idno>
              <idno type="halauthorid" notation="string">1528565-1213555</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0948-1600</idno>
              <affiliation ref="#struct-237002"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Haijun</forename>
                <surname>Liu</surname>
              </persName>
              <idno type="halauthorid">1201721-0</idno>
              <affiliation ref="#struct-237002"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Qianqian</forename>
                <surname>Song</surname>
              </persName>
              <idno type="halauthorid">2631384-0</idno>
              <affiliation ref="#struct-237002"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gemine</forename>
                <surname>Vivone</surname>
              </persName>
              <email type="md5">e9f5e7ab5bc98430d501047023c1ce89</email>
              <email type="domain">imaa.cnr.it</email>
              <idno type="idhal" notation="numeric">771980</idno>
              <idno type="halauthorid" notation="string">848055-771980</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9542-0638</idno>
              <affiliation ref="#struct-62720"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jocelyn</forename>
                <surname>Chanussot</surname>
              </persName>
              <email type="md5">fadb468ea31afc277adf894d9c5cf814</email>
              <email type="domain">gipsa-lab.grenoble-inp.fr</email>
              <idno type="idhal" notation="string">jocelyn-chanussot</idno>
              <idno type="idhal" notation="numeric">21313</idno>
              <idno type="halauthorid" notation="string">34285-21313</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4817-2875</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=6owK2OQAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/104503181</idno>
              <idno type="VIAF">https://viaf.org/viaf/311367442</idno>
              <affiliation ref="#struct-1043084"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Jocelyn</forename>
                <surname>Chanussot</surname>
              </persName>
              <email type="md5">1e1008b19d4868ade29a144b0a015530</email>
              <email type="domain">grenoble-inp.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-01-24 10:51:54</date>
              <date type="whenModified">2025-10-27 11:00:01</date>
              <date type="whenReleased">2025-01-24 10:51:54</date>
              <date type="whenProduced">2024</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1592283">
                <persName>
                  <forename>Jocelyn</forename>
                  <surname>Chanussot</surname>
                </persName>
                <email type="md5">1e1008b19d4868ade29a144b0a015530</email>
                <email type="domain">grenoble-inp.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04910119</idno>
            <idno type="halUri">https://hal.science/hal-04910119</idno>
            <idno type="halBibtex">zhou:hal-04910119</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE Transactions on Geoscience and Remote Sensing&lt;/i&gt;, 2024, 62, pp.1-15. &lt;a target="_blank" href="https://dx.doi.org/10.1109/TGRS.2024.3398038"&gt;&amp;#x27E8;10.1109/TGRS.2024.3398038&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE Transactions on Geoscience and Remote Sensing, 2024, 62, pp.1-15. &amp;#x27E8;10.1109/TGRS.2024.3398038&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="INRIA-RHA">INRIA Grenoble - Rhône-Alpes</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LJK">Laboratoire Jean Kuntzmann</idno>
            <idno type="stamp" n="LJK_GI" corresp="LJK">Département Géométrie et Images</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LJK-GI-THOTH" corresp="LJK_GI">Apprentissage de modèles visuels à partir de données massives</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">MeSAM: Multiscale Enhanced Segment Anything Model for Optical Remote Sensing Images</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Xichuan</forename>
                    <surname>Zhou</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1496384</idno>
                  <idno type="halauthorid" notation="string">3387107-1496384</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3304-3045</idno>
                  <affiliation ref="#struct-237002"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Fu</forename>
                    <surname>Liang</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1496385</idno>
                  <idno type="halauthorid" notation="string">3387108-1496385</idno>
                  <idno type="ORCID">https://orcid.org/0009-0008-1723-4651</idno>
                  <affiliation ref="#struct-237002"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Lihui</forename>
                    <surname>Chen</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1213555</idno>
                  <idno type="halauthorid" notation="string">1528565-1213555</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0948-1600</idno>
                  <affiliation ref="#struct-237002"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Haijun</forename>
                    <surname>Liu</surname>
                  </persName>
                  <idno type="halauthorid">1201721-0</idno>
                  <affiliation ref="#struct-237002"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Qianqian</forename>
                    <surname>Song</surname>
                  </persName>
                  <idno type="halauthorid">2631384-0</idno>
                  <affiliation ref="#struct-237002"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gemine</forename>
                    <surname>Vivone</surname>
                  </persName>
                  <email type="md5">e9f5e7ab5bc98430d501047023c1ce89</email>
                  <email type="domain">imaa.cnr.it</email>
                  <idno type="idhal" notation="numeric">771980</idno>
                  <idno type="halauthorid" notation="string">848055-771980</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9542-0638</idno>
                  <affiliation ref="#struct-62720"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jocelyn</forename>
                    <surname>Chanussot</surname>
                  </persName>
                  <email type="md5">fadb468ea31afc277adf894d9c5cf814</email>
                  <email type="domain">gipsa-lab.grenoble-inp.fr</email>
                  <idno type="idhal" notation="string">jocelyn-chanussot</idno>
                  <idno type="idhal" notation="numeric">21313</idno>
                  <idno type="halauthorid" notation="string">34285-21313</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4817-2875</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=6owK2OQAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/104503181</idno>
                  <idno type="VIAF">https://viaf.org/viaf/311367442</idno>
                  <affiliation ref="#struct-1043084"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">5377</idno>
                <idno type="issn">0196-2892</idno>
                <title level="j">IEEE Transactions on Geoscience and Remote Sensing</title>
                <imprint>
                  <publisher>Institute of Electrical and Electronics Engineers</publisher>
                  <biblScope unit="volume">62</biblScope>
                  <biblScope unit="pp">1-15</biblScope>
                  <date type="datePub">2024</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/TGRS.2024.3398038</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">High-frequency</term>
                <term xml:lang="en">Multiscale</term>
                <term xml:lang="en">Remote sensing</term>
                <term xml:lang="en">Segment anything model</term>
                <term xml:lang="en">Semantic segmentation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Segment anything model (SAM) has been widely applied to various downstream tasks for its excellent performance and generalization capability. However, SAM exhibits three limitations related to remote sensing (RS) semantic segmentation task: 1) the image encoders excessively lose high-frequency information, such as object boundaries and textures, resulting in rough segmentation masks; 2) due to being trained on natural images, SAM faces difficulty in accurately recognizing objects with large-scale variations and uneven distribution in RS images; and 3) the output tokens used for mask prediction are trained on natural images and not applicable to RS image segmentation. In this article, we explore an efficient paradigm for applying SAM to the semantic segmentation of RS images. Furthermore, we propose multiscale enhanced SAM (MeSAM), a new SAM fine-tuning method more suitable for RS images to adapt it to semantic segmentation tasks. Our method first introduces an inception mixer into the image encoder to effectively preserve high-frequency features. Second, by designing a mask decoder with RS correction and incorporating multiscale connections, we make up the difference in SAM from natural images to RS images. Experimental results demonstrated that our method significantly improves the segmentation accuracy of SAM for RS images, outperforming some state-of-the-art (SOTA) methods. The code will be available at https://github.com/Magic-lem/MeSAM.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-237002" status="VALID">
          <idno type="ROR">https://ror.org/023rhb549</idno>
          <orgName>Chongqing University [Chongqing]</orgName>
          <desc>
            <address>
              <addrLine>131 Yubei Rd, Shapingba, Chongqing</addrLine>
              <country key="CN"/>
            </address>
            <ref type="url">http://www.csc.edu.cn/studyinchina/universitydetailen.aspx?collegeId=116</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-62720" status="VALID">
          <orgName>Institute of Methodologies for Environmental Analysis of the National Research Council [Italy]</orgName>
          <orgName type="acronym">IMAA</orgName>
          <desc>
            <address>
              <addrLine>C.da S. Loja-Zona Industriale, 85050 Tito Scalo (PZ)</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">https://www.imaa.cnr.it/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-254021" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1043084" status="VALID">
          <idno type="IdRef">242196691</idno>
          <idno type="RNSR">201622034K</idno>
          <idno type="ROR">https://ror.org/02a2awp29</idno>
          <orgName>Apprentissage de modèles à partir de données massives</orgName>
          <orgName type="acronym">Thoth</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/thoth</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2497" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-1043077" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-254021" status="VALID">
          <idno type="ISNI">0000 0001 2159 6200</idno>
          <idno type="ROR">https://ror.org/04zaypm56</idno>
          <orgName>National Research Council of Italy | Consiglio Nazionale delle Ricerche</orgName>
          <orgName type="acronym">CNR</orgName>
          <date type="start">1923-01-01</date>
          <desc>
            <address>
              <addrLine>Piazzale Aldo Moro, 7 - 00185 Roma</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">https://www.cnr.it/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-2497" status="VALID">
          <idno type="RNSR">199218244V</idno>
          <idno type="ROR">https://ror.org/00n8d6z93</idno>
          <orgName>Centre Inria de l'Université Grenoble Alpes</orgName>
          <desc>
            <address>
              <addrLine>Inovallée655 avenue de l'Europe38330 Montbonnot</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/grenoble</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1043077" status="VALID">
          <idno type="IdRef">184945011</idno>
          <idno type="ISNI">0000 0004 0383 676X</idno>
          <idno type="RNSR">200711891Z</idno>
          <idno type="ROR">https://ror.org/04ett5b41</idno>
          <orgName>Laboratoire Jean Kuntzmann</orgName>
          <orgName type="acronym">LJK</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment IMAG, CS 40700, F-38058 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ljk.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>