Inducing Semantic Segmentation from an Example View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2006

AUTHORS

Yaar Schnitman , Yaron Caspi , Daniel Cohen-Or , Dani Lischinski

ABSTRACT

Segmenting an image into semantically meaningful parts is a fundamental and challenging task in computer vision. Automatic methods are able to segment an image into coherent regions, but such regions generally do not correspond to complete meaningful parts. In this paper, we show that even a single training example can greatly facilitate the induction of a semantically meaningful segmentation on novel images within the same domain: images depicting the same, or similar, objects in a similar setting. Our approach constructs a non-parametric representation of the example segmentation by selecting patch-based representatives. This allows us to represent complex semantic regions containing a large variety of colors and textures. Given an input image, we first partition it into small homogeneous fragments, and the possible labelings of each fragment are assessed using a robust voting procedure. Graph-cuts optimization is then used to label each fragment in a globally optimal manner. More... »

PAGES

373-384

References to SciGraph publications

  • 2002. Class-Specific, Top-Down Segmentation in COMPUTER VISION — ECCV 2002
  • Book

    TITLE

    Computer Vision – ACCV 2006

    ISBN

    978-3-540-31244-4
    978-3-540-32432-4

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/11612704_38

    DOI

    http://dx.doi.org/10.1007/11612704_38

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1035584643


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Tel Aviv University", 
              "id": "https://www.grid.ac/institutes/grid.12136.37", 
              "name": [
                "Tel Aviv University, Israel"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Schnitman", 
            "givenName": "Yaar", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Tel Aviv University", 
              "id": "https://www.grid.ac/institutes/grid.12136.37", 
              "name": [
                "Tel Aviv University, Israel"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Caspi", 
            "givenName": "Yaron", 
            "id": "sg:person.01262371651.41", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01262371651.41"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Tel Aviv University", 
              "id": "https://www.grid.ac/institutes/grid.12136.37", 
              "name": [
                "Tel Aviv University, Israel"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cohen-Or", 
            "givenName": "Daniel", 
            "id": "sg:person.013303512611.04", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013303512611.04"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Hebrew University of Jerusalem", 
              "id": "https://www.grid.ac/institutes/grid.9619.7", 
              "name": [
                "The Hebrew University of Jerusalem, Israel"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lischinski", 
            "givenName": "Dani", 
            "id": "sg:person.015570620407.86", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015570620407.86"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/3-540-47967-8_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026779540", 
              "https://doi.org/10.1007/3-540-47967-8_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1201775.882267", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035357893"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1015706.1015764", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039959794"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1015706.1015763", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039977361"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/566570.566576", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053046267"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.1000236", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061155588"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.868688", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157130"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.87344", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157139"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.969114", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157335"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/38.988747", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061164383"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1015706.1015719", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063148831"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1015706.1015720", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063148832"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2004.1315022", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094436314"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2001.937505", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095383001"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2006", 
        "datePublishedReg": "2006-01-01", 
        "description": "Segmenting an image into semantically meaningful parts is a fundamental and challenging task in computer vision. Automatic methods are able to segment an image into coherent regions, but such regions generally do not correspond to complete meaningful parts. In this paper, we show that even a single training example can greatly facilitate the induction of a semantically meaningful segmentation on novel images within the same domain: images depicting the same, or similar, objects in a similar setting. Our approach constructs a non-parametric representation of the example segmentation by selecting patch-based representatives. This allows us to represent complex semantic regions containing a large variety of colors and textures. Given an input image, we first partition it into small homogeneous fragments, and the possible labelings of each fragment are assessed using a robust voting procedure. Graph-cuts optimization is then used to label each fragment in a globally optimal manner.", 
        "editor": [
          {
            "familyName": "Narayanan", 
            "givenName": "P. J.", 
            "type": "Person"
          }, 
          {
            "familyName": "Nayar", 
            "givenName": "Shree K.", 
            "type": "Person"
          }, 
          {
            "familyName": "Shum", 
            "givenName": "Heung-Yeung", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/11612704_38", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-540-31244-4", 
            "978-3-540-32432-4"
          ], 
          "name": "Computer Vision \u2013 ACCV 2006", 
          "type": "Book"
        }, 
        "name": "Inducing Semantic Segmentation from an Example", 
        "pagination": "373-384", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/11612704_38"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "a982da2a5c5e48e7572deeac75451a567ec2a553b09162008547d2e1348215f0"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1035584643"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/11612704_38", 
          "https://app.dimensions.ai/details/publication/pub.1035584643"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T11:08", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8659_00000554.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/11612704_38"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/11612704_38'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11612704_38'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11612704_38'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11612704_38'


     

    This table displays all metadata directly associated to this object as RDF triples.

    141 TRIPLES      23 PREDICATES      41 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/11612704_38 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nb05de23eff4a4a5b95ec980ea6a7f169
    4 schema:citation sg:pub.10.1007/3-540-47967-8_8
    5 https://doi.org/10.1109/34.1000236
    6 https://doi.org/10.1109/34.868688
    7 https://doi.org/10.1109/34.87344
    8 https://doi.org/10.1109/34.969114
    9 https://doi.org/10.1109/38.988747
    10 https://doi.org/10.1109/cvpr.2004.1315022
    11 https://doi.org/10.1109/iccv.2001.937505
    12 https://doi.org/10.1145/1015706.1015719
    13 https://doi.org/10.1145/1015706.1015720
    14 https://doi.org/10.1145/1015706.1015763
    15 https://doi.org/10.1145/1015706.1015764
    16 https://doi.org/10.1145/1201775.882267
    17 https://doi.org/10.1145/566570.566576
    18 schema:datePublished 2006
    19 schema:datePublishedReg 2006-01-01
    20 schema:description Segmenting an image into semantically meaningful parts is a fundamental and challenging task in computer vision. Automatic methods are able to segment an image into coherent regions, but such regions generally do not correspond to complete meaningful parts. In this paper, we show that even a single training example can greatly facilitate the induction of a semantically meaningful segmentation on novel images within the same domain: images depicting the same, or similar, objects in a similar setting. Our approach constructs a non-parametric representation of the example segmentation by selecting patch-based representatives. This allows us to represent complex semantic regions containing a large variety of colors and textures. Given an input image, we first partition it into small homogeneous fragments, and the possible labelings of each fragment are assessed using a robust voting procedure. Graph-cuts optimization is then used to label each fragment in a globally optimal manner.
    21 schema:editor N47ca17c423a3467d818fa7bd25413cf7
    22 schema:genre chapter
    23 schema:inLanguage en
    24 schema:isAccessibleForFree false
    25 schema:isPartOf Nb7ff128fca4942cdbc8dfe6b7316173f
    26 schema:name Inducing Semantic Segmentation from an Example
    27 schema:pagination 373-384
    28 schema:productId N1c0a3b87630b4b9ca1bcb0fb17fdf014
    29 N4cfd3a040fe8433f86d1733b8e662af7
    30 N93aa4afa43014690afdcbf492e792d8b
    31 schema:publisher N101bd8eb9311418ea378a44b34e92647
    32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035584643
    33 https://doi.org/10.1007/11612704_38
    34 schema:sdDatePublished 2019-04-15T11:08
    35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    36 schema:sdPublisher N5e05c32d8e484a7d88a364d6928f36b5
    37 schema:url http://link.springer.com/10.1007/11612704_38
    38 sgo:license sg:explorer/license/
    39 sgo:sdDataset chapters
    40 rdf:type schema:Chapter
    41 N068a8867719f493c864ff5ddb2912269 rdf:first sg:person.015570620407.86
    42 rdf:rest rdf:nil
    43 N0fb78caf14e54c07b6bba4e3469715d4 rdf:first N2b04509e6a234bc0b62398dbb08c9523
    44 rdf:rest N995b0351e26a4c269b7e5550902fbedd
    45 N101bd8eb9311418ea378a44b34e92647 schema:location Berlin, Heidelberg
    46 schema:name Springer Berlin Heidelberg
    47 rdf:type schema:Organisation
    48 N12db5983581c447d918bf65a0ce4d3a4 schema:familyName Shum
    49 schema:givenName Heung-Yeung
    50 rdf:type schema:Person
    51 N1c0a3b87630b4b9ca1bcb0fb17fdf014 schema:name dimensions_id
    52 schema:value pub.1035584643
    53 rdf:type schema:PropertyValue
    54 N2b04509e6a234bc0b62398dbb08c9523 schema:familyName Nayar
    55 schema:givenName Shree K.
    56 rdf:type schema:Person
    57 N2f8af1999a0f4483843f6ee95f3a893b schema:affiliation https://www.grid.ac/institutes/grid.12136.37
    58 schema:familyName Schnitman
    59 schema:givenName Yaar
    60 rdf:type schema:Person
    61 N3e21876ef4e947ef876aa043c49bac67 schema:familyName Narayanan
    62 schema:givenName P. J.
    63 rdf:type schema:Person
    64 N47ca17c423a3467d818fa7bd25413cf7 rdf:first N3e21876ef4e947ef876aa043c49bac67
    65 rdf:rest N0fb78caf14e54c07b6bba4e3469715d4
    66 N4cfd3a040fe8433f86d1733b8e662af7 schema:name readcube_id
    67 schema:value a982da2a5c5e48e7572deeac75451a567ec2a553b09162008547d2e1348215f0
    68 rdf:type schema:PropertyValue
    69 N5e05c32d8e484a7d88a364d6928f36b5 schema:name Springer Nature - SN SciGraph project
    70 rdf:type schema:Organization
    71 N816cba911379469ea78b4ae29c97dd9d rdf:first sg:person.013303512611.04
    72 rdf:rest N068a8867719f493c864ff5ddb2912269
    73 N93aa4afa43014690afdcbf492e792d8b schema:name doi
    74 schema:value 10.1007/11612704_38
    75 rdf:type schema:PropertyValue
    76 N995b0351e26a4c269b7e5550902fbedd rdf:first N12db5983581c447d918bf65a0ce4d3a4
    77 rdf:rest rdf:nil
    78 Nb05de23eff4a4a5b95ec980ea6a7f169 rdf:first N2f8af1999a0f4483843f6ee95f3a893b
    79 rdf:rest Nc77792b4d79e4db58c441beb176912b6
    80 Nb7ff128fca4942cdbc8dfe6b7316173f schema:isbn 978-3-540-31244-4
    81 978-3-540-32432-4
    82 schema:name Computer Vision – ACCV 2006
    83 rdf:type schema:Book
    84 Nc77792b4d79e4db58c441beb176912b6 rdf:first sg:person.01262371651.41
    85 rdf:rest N816cba911379469ea78b4ae29c97dd9d
    86 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    87 schema:name Information and Computing Sciences
    88 rdf:type schema:DefinedTerm
    89 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    90 schema:name Artificial Intelligence and Image Processing
    91 rdf:type schema:DefinedTerm
    92 sg:person.01262371651.41 schema:affiliation https://www.grid.ac/institutes/grid.12136.37
    93 schema:familyName Caspi
    94 schema:givenName Yaron
    95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01262371651.41
    96 rdf:type schema:Person
    97 sg:person.013303512611.04 schema:affiliation https://www.grid.ac/institutes/grid.12136.37
    98 schema:familyName Cohen-Or
    99 schema:givenName Daniel
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013303512611.04
    101 rdf:type schema:Person
    102 sg:person.015570620407.86 schema:affiliation https://www.grid.ac/institutes/grid.9619.7
    103 schema:familyName Lischinski
    104 schema:givenName Dani
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015570620407.86
    106 rdf:type schema:Person
    107 sg:pub.10.1007/3-540-47967-8_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026779540
    108 https://doi.org/10.1007/3-540-47967-8_8
    109 rdf:type schema:CreativeWork
    110 https://doi.org/10.1109/34.1000236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155588
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1109/34.868688 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157130
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1109/34.87344 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157139
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1109/34.969114 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157335
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1109/38.988747 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061164383
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1109/cvpr.2004.1315022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094436314
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1109/iccv.2001.937505 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095383001
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1145/1015706.1015719 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063148831
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1145/1015706.1015720 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063148832
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1145/1015706.1015763 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039977361
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1145/1015706.1015764 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039959794
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1145/1201775.882267 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035357893
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.1145/566570.566576 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053046267
    135 rdf:type schema:CreativeWork
    136 https://www.grid.ac/institutes/grid.12136.37 schema:alternateName Tel Aviv University
    137 schema:name Tel Aviv University, Israel
    138 rdf:type schema:Organization
    139 https://www.grid.ac/institutes/grid.9619.7 schema:alternateName Hebrew University of Jerusalem
    140 schema:name The Hebrew University of Jerusalem, Israel
    141 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...