FPANet: Feature-enhanced position attention network for semantic segmentation View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2021-09-25

AUTHORS

Haixia Xu, Shuailong Wang, Yunjia Huang, Wei Zhou, Qi Chen, Dongbo Zhang

ABSTRACT

Attention mechanism is beneficial to capture the contextual information in visual task. This paper proposes a feature-enhanced position attention network (FPANet) for semantic segmentation based on framework of FCN. On the top of dilated FCN, we design a feature integration module, which aggregates the context over local features by expanding the receptive field and multiscale representation, to promote a position attention module, which models spatial interdependencies over features, so as to form a feature-enhanced position attention module to enhance the discrimination of features for better semantic segmentation. Experimental comparisons show that our proposed FPANet is superior to other state-of-the-art models in the performance of segmentation accuracy on datasets PASCAL VOC 2012 and Cityscapes. More... »

PAGES

119

References to SciGraph publications

  • 2009-09-09. The Pascal Visual Object Classes (VOC) Challenge in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2016-08-27. Convolutional Scale Invariance for Semantic Segmentation in PATTERN RECOGNITION
  • 2018-10-06. Adaptive Affinity Fields for Semantic Segmentation in COMPUTER VISION – ECCV 2018
  • 2020-11-07. Object-Contextual Representations for Semantic Segmentation in COMPUTER VISION – ECCV 2020
  • 2016-09-17. Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation in COMPUTER VISION – ECCV 2016
  • 2018-10-06. CBAM: Convolutional Block Attention Module in COMPUTER VISION – ECCV 2018
  • 2015-11-18. U-Net: Convolutional Networks for Biomedical Image Segmentation in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION – MICCAI 2015
  • 2020-11-19. Deep semantic segmentation-based multiple description coding in MULTIMEDIA TOOLS AND APPLICATIONS
  • 2018-10-05. PSANet: Point-wise Spatial Attention Network for Scene Parsing in COMPUTER VISION – ECCV 2018
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00138-021-01246-x

    DOI

    http://dx.doi.org/10.1007/s00138-021-01246-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1141395198


    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/2008/17", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology and Cognitive Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "School of Automation and Electronic Information, XiangTan University, Xiangtan, China", 
              "id": "http://www.grid.ac/institutes/grid.412982.4", 
              "name": [
                "School of Automation and Electronic Information, XiangTan University, Xiangtan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Xu", 
            "givenName": "Haixia", 
            "id": "sg:person.014527172467.75", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014527172467.75"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Automation and Electronic Information, XiangTan University, Xiangtan, China", 
              "id": "http://www.grid.ac/institutes/grid.412982.4", 
              "name": [
                "School of Automation and Electronic Information, XiangTan University, Xiangtan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Shuailong", 
            "id": "sg:person.014167064305.48", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014167064305.48"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Automation and Electronic Information, XiangTan University, Xiangtan, China", 
              "id": "http://www.grid.ac/institutes/grid.412982.4", 
              "name": [
                "School of Automation and Electronic Information, XiangTan University, Xiangtan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Huang", 
            "givenName": "Yunjia", 
            "id": "sg:person.010423074011.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010423074011.53"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Automation and Electronic Information, XiangTan University, Xiangtan, China", 
              "id": "http://www.grid.ac/institutes/grid.412982.4", 
              "name": [
                "School of Automation and Electronic Information, XiangTan University, Xiangtan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhou", 
            "givenName": "Wei", 
            "id": "sg:person.015620625573.02", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015620625573.02"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Automation and Electronic Information, XiangTan University, Xiangtan, China", 
              "id": "http://www.grid.ac/institutes/grid.412982.4", 
              "name": [
                "School of Automation and Electronic Information, XiangTan University, Xiangtan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chen", 
            "givenName": "Qi", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Automation and Electronic Information, XiangTan University, Xiangtan, China", 
              "id": "http://www.grid.ac/institutes/grid.412982.4", 
              "name": [
                "School of Automation and Electronic Information, XiangTan University, Xiangtan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhang", 
            "givenName": "Dongbo", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-319-45886-1_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001427984", 
              "https://doi.org/10.1007/978-3-319-45886-1_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11042-020-09283-w", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1132778785", 
              "https://doi.org/10.1007/s11042-020-09283-w"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-24574-4_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017774818", 
              "https://doi.org/10.1007/978-3-319-24574-4_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01234-2_1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107454571", 
              "https://doi.org/10.1007/978-3-030-01234-2_1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01240-3_17", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107463349", 
              "https://doi.org/10.1007/978-3-030-01240-3_17"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01246-5_36", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107454649", 
              "https://doi.org/10.1007/978-3-030-01246-5_36"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-009-0275-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014796149", 
              "https://doi.org/10.1007/s11263-009-0275-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-46487-9_32", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014346769", 
              "https://doi.org/10.1007/978-3-319-46487-9_32"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-58539-6_11", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1132404102", 
              "https://doi.org/10.1007/978-3-030-58539-6_11"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2021-09-25", 
        "datePublishedReg": "2021-09-25", 
        "description": "Attention mechanism is beneficial to capture the contextual information in visual task. This paper proposes a feature-enhanced position attention network (FPANet) for semantic segmentation based on framework of FCN. On the top of dilated FCN, we design a feature integration module, which aggregates the context over local features by expanding the receptive field and multiscale representation, to promote a position attention module, which models spatial interdependencies over features, so as to form a feature-enhanced position attention module to enhance the discrimination of features for better semantic segmentation. Experimental comparisons show that our proposed FPANet is superior to other state-of-the-art models in the performance of segmentation accuracy on datasets PASCAL VOC 2012 and Cityscapes.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s00138-021-01246-x", 
        "inLanguage": "en", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1045266", 
            "issn": [
              "0932-8092", 
              "1432-1769"
            ], 
            "name": "Machine Vision and Applications", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "6", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "32"
          }
        ], 
        "keywords": [
          "semantic segmentation", 
          "position attention module", 
          "attention module", 
          "feature integration module", 
          "attention network", 
          "good semantic segmentation", 
          "PASCAL VOC 2012", 
          "discrimination of features", 
          "VOC 2012", 
          "attention mechanism", 
          "segmentation accuracy", 
          "contextual information", 
          "integration module", 
          "art models", 
          "local features", 
          "multiscale representation", 
          "segmentation", 
          "visual tasks", 
          "FCN", 
          "experimental comparison", 
          "network", 
          "module", 
          "receptive fields", 
          "features", 
          "task", 
          "cityscape", 
          "framework", 
          "representation", 
          "accuracy", 
          "information", 
          "interdependencies", 
          "spatial interdependencies", 
          "discrimination", 
          "performance", 
          "context", 
          "top", 
          "model", 
          "field", 
          "state", 
          "comparison", 
          "mechanism", 
          "paper", 
          "feature-enhanced position attention network", 
          "position attention network", 
          "framework of FCN", 
          "dilated FCN", 
          "feature-enhanced position attention module", 
          "FPANet", 
          "datasets PASCAL VOC 2012"
        ], 
        "name": "FPANet: Feature-enhanced position attention network for semantic segmentation", 
        "pagination": "119", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1141395198"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00138-021-01246-x"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00138-021-01246-x", 
          "https://app.dimensions.ai/details/publication/pub.1141395198"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-01-01T19:02", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_901.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s00138-021-01246-x"
      }
    ]
     

    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/s00138-021-01246-x'

    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/s00138-021-01246-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00138-021-01246-x'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00138-021-01246-x'


     

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

    176 TRIPLES      22 PREDICATES      83 URIs      66 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00138-021-01246-x schema:about anzsrc-for:17
    2 anzsrc-for:1701
    3 schema:author N822c5d5df5784a169906c1a816209170
    4 schema:citation sg:pub.10.1007/978-3-030-01234-2_1
    5 sg:pub.10.1007/978-3-030-01240-3_17
    6 sg:pub.10.1007/978-3-030-01246-5_36
    7 sg:pub.10.1007/978-3-030-58539-6_11
    8 sg:pub.10.1007/978-3-319-24574-4_28
    9 sg:pub.10.1007/978-3-319-45886-1_6
    10 sg:pub.10.1007/978-3-319-46487-9_32
    11 sg:pub.10.1007/s11042-020-09283-w
    12 sg:pub.10.1007/s11263-009-0275-4
    13 schema:datePublished 2021-09-25
    14 schema:datePublishedReg 2021-09-25
    15 schema:description Attention mechanism is beneficial to capture the contextual information in visual task. This paper proposes a feature-enhanced position attention network (FPANet) for semantic segmentation based on framework of FCN. On the top of dilated FCN, we design a feature integration module, which aggregates the context over local features by expanding the receptive field and multiscale representation, to promote a position attention module, which models spatial interdependencies over features, so as to form a feature-enhanced position attention module to enhance the discrimination of features for better semantic segmentation. Experimental comparisons show that our proposed FPANet is superior to other state-of-the-art models in the performance of segmentation accuracy on datasets PASCAL VOC 2012 and Cityscapes.
    16 schema:genre article
    17 schema:inLanguage en
    18 schema:isAccessibleForFree false
    19 schema:isPartOf N6943285b3b5b47cc95617352802328b3
    20 Na05eed6c233241bd8f248cc3710429aa
    21 sg:journal.1045266
    22 schema:keywords FCN
    23 FPANet
    24 PASCAL VOC 2012
    25 VOC 2012
    26 accuracy
    27 art models
    28 attention mechanism
    29 attention module
    30 attention network
    31 cityscape
    32 comparison
    33 context
    34 contextual information
    35 datasets PASCAL VOC 2012
    36 dilated FCN
    37 discrimination
    38 discrimination of features
    39 experimental comparison
    40 feature integration module
    41 feature-enhanced position attention module
    42 feature-enhanced position attention network
    43 features
    44 field
    45 framework
    46 framework of FCN
    47 good semantic segmentation
    48 information
    49 integration module
    50 interdependencies
    51 local features
    52 mechanism
    53 model
    54 module
    55 multiscale representation
    56 network
    57 paper
    58 performance
    59 position attention module
    60 position attention network
    61 receptive fields
    62 representation
    63 segmentation
    64 segmentation accuracy
    65 semantic segmentation
    66 spatial interdependencies
    67 state
    68 task
    69 top
    70 visual tasks
    71 schema:name FPANet: Feature-enhanced position attention network for semantic segmentation
    72 schema:pagination 119
    73 schema:productId N0984b764afd74b9fac367f73f1c06d5b
    74 N5ff965edb18c4baa8252f3f38c38efa3
    75 schema:sameAs https://app.dimensions.ai/details/publication/pub.1141395198
    76 https://doi.org/10.1007/s00138-021-01246-x
    77 schema:sdDatePublished 2022-01-01T19:02
    78 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    79 schema:sdPublisher N3a148243f3904c38a9e0bc63126d0175
    80 schema:url https://doi.org/10.1007/s00138-021-01246-x
    81 sgo:license sg:explorer/license/
    82 sgo:sdDataset articles
    83 rdf:type schema:ScholarlyArticle
    84 N0984b764afd74b9fac367f73f1c06d5b schema:name dimensions_id
    85 schema:value pub.1141395198
    86 rdf:type schema:PropertyValue
    87 N15f919d759314691aa5c6bbe9d811318 schema:affiliation grid-institutes:grid.412982.4
    88 schema:familyName Zhang
    89 schema:givenName Dongbo
    90 rdf:type schema:Person
    91 N350d90f61a7a46a0b669676c7656fe08 rdf:first sg:person.014167064305.48
    92 rdf:rest N6f2891f5b1474cc2b976874a092752e1
    93 N3a148243f3904c38a9e0bc63126d0175 schema:name Springer Nature - SN SciGraph project
    94 rdf:type schema:Organization
    95 N5ff965edb18c4baa8252f3f38c38efa3 schema:name doi
    96 schema:value 10.1007/s00138-021-01246-x
    97 rdf:type schema:PropertyValue
    98 N6943285b3b5b47cc95617352802328b3 schema:issueNumber 6
    99 rdf:type schema:PublicationIssue
    100 N6f2891f5b1474cc2b976874a092752e1 rdf:first sg:person.010423074011.53
    101 rdf:rest N896827a5474741dfbcaa2b1481d4bc58
    102 N822c5d5df5784a169906c1a816209170 rdf:first sg:person.014527172467.75
    103 rdf:rest N350d90f61a7a46a0b669676c7656fe08
    104 N896827a5474741dfbcaa2b1481d4bc58 rdf:first sg:person.015620625573.02
    105 rdf:rest Nc9324ad8e2584e65978690159fab7aca
    106 N92145f3a6ae2411bb86850e171b8a5c7 schema:affiliation grid-institutes:grid.412982.4
    107 schema:familyName Chen
    108 schema:givenName Qi
    109 rdf:type schema:Person
    110 Na05eed6c233241bd8f248cc3710429aa schema:volumeNumber 32
    111 rdf:type schema:PublicationVolume
    112 Nc9324ad8e2584e65978690159fab7aca rdf:first N92145f3a6ae2411bb86850e171b8a5c7
    113 rdf:rest Nfd18c1748a514fc3ae29ae1297250074
    114 Nfd18c1748a514fc3ae29ae1297250074 rdf:first N15f919d759314691aa5c6bbe9d811318
    115 rdf:rest rdf:nil
    116 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
    117 schema:name Psychology and Cognitive Sciences
    118 rdf:type schema:DefinedTerm
    119 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
    120 schema:name Psychology
    121 rdf:type schema:DefinedTerm
    122 sg:journal.1045266 schema:issn 0932-8092
    123 1432-1769
    124 schema:name Machine Vision and Applications
    125 schema:publisher Springer Nature
    126 rdf:type schema:Periodical
    127 sg:person.010423074011.53 schema:affiliation grid-institutes:grid.412982.4
    128 schema:familyName Huang
    129 schema:givenName Yunjia
    130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010423074011.53
    131 rdf:type schema:Person
    132 sg:person.014167064305.48 schema:affiliation grid-institutes:grid.412982.4
    133 schema:familyName Wang
    134 schema:givenName Shuailong
    135 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014167064305.48
    136 rdf:type schema:Person
    137 sg:person.014527172467.75 schema:affiliation grid-institutes:grid.412982.4
    138 schema:familyName Xu
    139 schema:givenName Haixia
    140 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014527172467.75
    141 rdf:type schema:Person
    142 sg:person.015620625573.02 schema:affiliation grid-institutes:grid.412982.4
    143 schema:familyName Zhou
    144 schema:givenName Wei
    145 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015620625573.02
    146 rdf:type schema:Person
    147 sg:pub.10.1007/978-3-030-01234-2_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454571
    148 https://doi.org/10.1007/978-3-030-01234-2_1
    149 rdf:type schema:CreativeWork
    150 sg:pub.10.1007/978-3-030-01240-3_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107463349
    151 https://doi.org/10.1007/978-3-030-01240-3_17
    152 rdf:type schema:CreativeWork
    153 sg:pub.10.1007/978-3-030-01246-5_36 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454649
    154 https://doi.org/10.1007/978-3-030-01246-5_36
    155 rdf:type schema:CreativeWork
    156 sg:pub.10.1007/978-3-030-58539-6_11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132404102
    157 https://doi.org/10.1007/978-3-030-58539-6_11
    158 rdf:type schema:CreativeWork
    159 sg:pub.10.1007/978-3-319-24574-4_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017774818
    160 https://doi.org/10.1007/978-3-319-24574-4_28
    161 rdf:type schema:CreativeWork
    162 sg:pub.10.1007/978-3-319-45886-1_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001427984
    163 https://doi.org/10.1007/978-3-319-45886-1_6
    164 rdf:type schema:CreativeWork
    165 sg:pub.10.1007/978-3-319-46487-9_32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014346769
    166 https://doi.org/10.1007/978-3-319-46487-9_32
    167 rdf:type schema:CreativeWork
    168 sg:pub.10.1007/s11042-020-09283-w schema:sameAs https://app.dimensions.ai/details/publication/pub.1132778785
    169 https://doi.org/10.1007/s11042-020-09283-w
    170 rdf:type schema:CreativeWork
    171 sg:pub.10.1007/s11263-009-0275-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014796149
    172 https://doi.org/10.1007/s11263-009-0275-4
    173 rdf:type schema:CreativeWork
    174 grid-institutes:grid.412982.4 schema:alternateName School of Automation and Electronic Information, XiangTan University, Xiangtan, China
    175 schema:name School of Automation and Electronic Information, XiangTan University, Xiangtan, China
    176 rdf:type schema:Organization
     




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


    ...