Learning Dilation Factors for Semantic Segmentation of Street Scenes View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2017-08-15

AUTHORS

Yang He , Margret Keuper , Bernt Schiele , Mario Fritz

ABSTRACT

Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently large receptive fields is non trivial. This is even more so, when objects or classes present in an image significantly vary in size. Dilated convolutions have proven valuable for semantic segmentation, because they allow to increase the size of the receptive field without sacrificing image resolution. However, in current state-of-the-art methods, dilation parameters are hand-tuned and fixed. In this paper, we present an approach for learning dilation parameters adaptively per channel, consistently improving semantic segmentation results on street-scene datasets like Cityscapes and Camvid. More... »

PAGES

41-51

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-66709-6_4

DOI

http://dx.doi.org/10.1007/978-3-319-66709-6_4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1091259721


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "He", 
        "givenName": "Yang", 
        "id": "sg:person.010655401332.41", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010655401332.41"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Mannheim, Mannheim, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5601.2", 
          "name": [
            "University of Mannheim, Mannheim, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Keuper", 
        "givenName": "Margret", 
        "id": "sg:person.013477515133.33", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013477515133.33"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Schiele", 
        "givenName": "Bernt", 
        "id": "sg:person.01174260421.90", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01174260421.90"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Mario", 
        "id": "sg:person.013361072755.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2017-08-15", 
    "datePublishedReg": "2017-08-15", 
    "description": "Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently large receptive fields is non trivial. This is even more so, when objects or classes present in an image significantly vary in size. Dilated convolutions have proven valuable for semantic segmentation, because they allow to increase the size of the receptive field without sacrificing image resolution. However, in current state-of-the-art methods, dilation parameters are hand-tuned and fixed. In this paper, we present an approach for learning dilation parameters adaptively per channel, consistently improving semantic segmentation results on street-scene datasets like Cityscapes and Camvid.", 
    "editor": [
      {
        "familyName": "Roth", 
        "givenName": "Volker", 
        "type": "Person"
      }, 
      {
        "familyName": "Vetter", 
        "givenName": "Thomas", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-66709-6_4", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-66708-9", 
        "978-3-319-66709-6"
      ], 
      "name": "Pattern Recognition", 
      "type": "Book"
    }, 
    "keywords": [
      "semantic segmentation", 
      "street scene datasets", 
      "semantic segmentation results", 
      "segmentation results", 
      "art methods", 
      "contextual information", 
      "large receptive fields", 
      "street scenes", 
      "segmentation", 
      "image resolution", 
      "receptive fields", 
      "dilation parameter", 
      "current state", 
      "CamVid", 
      "fine details", 
      "dilation factor", 
      "same time", 
      "dataset", 
      "scene", 
      "convolution", 
      "cityscape", 
      "images", 
      "objects", 
      "information", 
      "field", 
      "method", 
      "channels", 
      "detail", 
      "class", 
      "parameters", 
      "time", 
      "state", 
      "results", 
      "size", 
      "resolution", 
      "factors", 
      "paper", 
      "approach"
    ], 
    "name": "Learning Dilation Factors for Semantic Segmentation of Street Scenes", 
    "pagination": "41-51", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1091259721"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-66709-6_4"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-66709-6_4", 
      "https://app.dimensions.ai/details/publication/pub.1091259721"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:47", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_183.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-66709-6_4"
  }
]
 

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.10.1007/978-3-319-66709-6_4'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66709-6_4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66709-6_4'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-66709-6_4'


 

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

126 TRIPLES      22 PREDICATES      62 URIs      55 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-66709-6_4 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nfa0775ed8cb742979a5c54367dc61b5d
4 schema:datePublished 2017-08-15
5 schema:datePublishedReg 2017-08-15
6 schema:description Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently large receptive fields is non trivial. This is even more so, when objects or classes present in an image significantly vary in size. Dilated convolutions have proven valuable for semantic segmentation, because they allow to increase the size of the receptive field without sacrificing image resolution. However, in current state-of-the-art methods, dilation parameters are hand-tuned and fixed. In this paper, we present an approach for learning dilation parameters adaptively per channel, consistently improving semantic segmentation results on street-scene datasets like Cityscapes and Camvid.
7 schema:editor Nd07b357b4c25490fbee7c40f0beabd5e
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N1bf1d775ca0841a685dddaff3277a5ea
11 schema:keywords CamVid
12 approach
13 art methods
14 channels
15 cityscape
16 class
17 contextual information
18 convolution
19 current state
20 dataset
21 detail
22 dilation factor
23 dilation parameter
24 factors
25 field
26 fine details
27 image resolution
28 images
29 information
30 large receptive fields
31 method
32 objects
33 paper
34 parameters
35 receptive fields
36 resolution
37 results
38 same time
39 scene
40 segmentation
41 segmentation results
42 semantic segmentation
43 semantic segmentation results
44 size
45 state
46 street scene datasets
47 street scenes
48 time
49 schema:name Learning Dilation Factors for Semantic Segmentation of Street Scenes
50 schema:pagination 41-51
51 schema:productId N4a9997a13eda44dbb3a80d56d3a644be
52 Na28079d283014968bbf5b3b8e62ac34b
53 schema:publisher N3b180c5fdb944ace843f2cf6529c959b
54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091259721
55 https://doi.org/10.1007/978-3-319-66709-6_4
56 schema:sdDatePublished 2022-12-01T06:47
57 schema:sdLicense https://scigraph.springernature.com/explorer/license/
58 schema:sdPublisher N557c85efd8da46ff93a9b53122606b67
59 schema:url https://doi.org/10.1007/978-3-319-66709-6_4
60 sgo:license sg:explorer/license/
61 sgo:sdDataset chapters
62 rdf:type schema:Chapter
63 N1b159f2e006f4c309ac73891b7eea2d9 rdf:first sg:person.01174260421.90
64 rdf:rest Nff2d3200faa1473c9daa098c754776f3
65 N1bf1d775ca0841a685dddaff3277a5ea schema:isbn 978-3-319-66708-9
66 978-3-319-66709-6
67 schema:name Pattern Recognition
68 rdf:type schema:Book
69 N356db1bcd74e40b6b4f2baf8d55ba4b0 rdf:first N7cf1983c40704741a92c676adc98dcb7
70 rdf:rest rdf:nil
71 N3b180c5fdb944ace843f2cf6529c959b schema:name Springer Nature
72 rdf:type schema:Organisation
73 N4a9997a13eda44dbb3a80d56d3a644be schema:name doi
74 schema:value 10.1007/978-3-319-66709-6_4
75 rdf:type schema:PropertyValue
76 N557c85efd8da46ff93a9b53122606b67 schema:name Springer Nature - SN SciGraph project
77 rdf:type schema:Organization
78 N7cf1983c40704741a92c676adc98dcb7 schema:familyName Vetter
79 schema:givenName Thomas
80 rdf:type schema:Person
81 N8728ffae50dc48ce9030275a8537d900 rdf:first sg:person.013477515133.33
82 rdf:rest N1b159f2e006f4c309ac73891b7eea2d9
83 N900adee8dcc34be8b24b6fdf66fadb6a schema:familyName Roth
84 schema:givenName Volker
85 rdf:type schema:Person
86 Na28079d283014968bbf5b3b8e62ac34b schema:name dimensions_id
87 schema:value pub.1091259721
88 rdf:type schema:PropertyValue
89 Nd07b357b4c25490fbee7c40f0beabd5e rdf:first N900adee8dcc34be8b24b6fdf66fadb6a
90 rdf:rest N356db1bcd74e40b6b4f2baf8d55ba4b0
91 Nfa0775ed8cb742979a5c54367dc61b5d rdf:first sg:person.010655401332.41
92 rdf:rest N8728ffae50dc48ce9030275a8537d900
93 Nff2d3200faa1473c9daa098c754776f3 rdf:first sg:person.013361072755.17
94 rdf:rest rdf:nil
95 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
96 schema:name Information and Computing Sciences
97 rdf:type schema:DefinedTerm
98 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
99 schema:name Artificial Intelligence and Image Processing
100 rdf:type schema:DefinedTerm
101 sg:person.010655401332.41 schema:affiliation grid-institutes:grid.419528.3
102 schema:familyName He
103 schema:givenName Yang
104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010655401332.41
105 rdf:type schema:Person
106 sg:person.01174260421.90 schema:affiliation grid-institutes:grid.419528.3
107 schema:familyName Schiele
108 schema:givenName Bernt
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01174260421.90
110 rdf:type schema:Person
111 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.419528.3
112 schema:familyName Fritz
113 schema:givenName Mario
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
115 rdf:type schema:Person
116 sg:person.013477515133.33 schema:affiliation grid-institutes:grid.5601.2
117 schema:familyName Keuper
118 schema:givenName Margret
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013477515133.33
120 rdf:type schema:Person
121 grid-institutes:grid.419528.3 schema:alternateName Max Planck Institute for Informatics, Saarbrücken, Germany
122 schema:name Max Planck Institute for Informatics, Saarbrücken, Germany
123 rdf:type schema:Organization
124 grid-institutes:grid.5601.2 schema:alternateName University of Mannheim, Mannheim, Germany
125 schema:name University of Mannheim, Mannheim, Germany
126 rdf:type schema:Organization
 




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


...