Adapting Visual Category Models to New Domains View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2010

AUTHORS

Kate Saenko , Brian Kulis , Mario Fritz , Trevor Darrell

ABSTRACT

Domain adaptation is an important emerging topic in computer vision. In this paper, we present one of the first studies of domain shift in the context of object recognition. We introduce a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. The transformation is learned in a supervised manner and can be applied to categories for which there are no labeled examples in the new domain. While we focus our evaluation on object recognition tasks, the transform-based adaptation technique we develop is general and could be applied to non-image data. Another contribution is a new multi-domain object database, freely available for download. We experimentally demonstrate the ability of our method to improve recognition on categories with few or no target domain labels and moderate to large changes in the imaging conditions. More... »

PAGES

213-226

Book

TITLE

Computer Vision – ECCV 2010

ISBN

978-3-642-15560-4
978-3-642-15561-1

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_16

DOI

http://dx.doi.org/10.1007/978-3-642-15561-1_16

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1047848527


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": "UC Berkeley EECS and ICSI, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley EECS and ICSI, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Saenko", 
        "givenName": "Kate", 
        "id": "sg:person.0617252060.44", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0617252060.44"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "UC Berkeley EECS and ICSI, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley EECS and ICSI, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kulis", 
        "givenName": "Brian", 
        "id": "sg:person.01046073067.44", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01046073067.44"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "UC Berkeley EECS and ICSI, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley EECS and ICSI, Berkeley, CA"
          ], 
          "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"
      }, 
      {
        "affiliation": {
          "alternateName": "UC Berkeley EECS and ICSI, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "UC Berkeley EECS and ICSI, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Darrell", 
        "givenName": "Trevor", 
        "id": "sg:person.01001613660.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01001613660.25"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2010", 
    "datePublishedReg": "2010-01-01", 
    "description": "Domain adaptation is an important emerging topic in computer vision. In this paper, we present one of the first studies of domain shift in the context of object recognition. We introduce a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. The transformation is learned in a supervised manner and can be applied to categories for which there are no labeled examples in the new domain. While we focus our evaluation on object recognition tasks, the transform-based adaptation technique we develop is general and could be applied to non-image data. Another contribution is a new multi-domain object database, freely available for download. We experimentally demonstrate the ability of our method to improve recognition on categories with few or no target domain labels and moderate to large changes in the imaging conditions.", 
    "editor": [
      {
        "familyName": "Daniilidis", 
        "givenName": "Kostas", 
        "type": "Person"
      }, 
      {
        "familyName": "Maragos", 
        "givenName": "Petros", 
        "type": "Person"
      }, 
      {
        "familyName": "Paragios", 
        "givenName": "Nikos", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-15561-1_16", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-15560-4", 
        "978-3-642-15561-1"
      ], 
      "name": "Computer Vision \u2013 ECCV 2010", 
      "type": "Book"
    }, 
    "keywords": [
      "non-image data", 
      "new domain", 
      "target domain labels", 
      "computer vision", 
      "object databases", 
      "domain adaptation", 
      "domain shift", 
      "object model", 
      "domain labels", 
      "supervised manner", 
      "feature distribution", 
      "object recognition", 
      "adaptation techniques", 
      "recognition task", 
      "object recognition task", 
      "visual domain", 
      "category model", 
      "recognition", 
      "download", 
      "domain", 
      "task", 
      "vision", 
      "labels", 
      "database", 
      "model", 
      "method", 
      "topic", 
      "technique", 
      "example", 
      "categories", 
      "context", 
      "transformation", 
      "data", 
      "adaptation", 
      "evaluation", 
      "manner", 
      "ability", 
      "contribution", 
      "first study", 
      "distribution", 
      "conditions", 
      "changes", 
      "study", 
      "large changes", 
      "shift", 
      "effect", 
      "paper"
    ], 
    "name": "Adapting Visual Category Models to New Domains", 
    "pagination": "213-226", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1047848527"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-15561-1_16"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-15561-1_16", 
      "https://app.dimensions.ai/details/publication/pub.1047848527"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:54", 
    "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_476.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-15561-1_16"
  }
]
 

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.10.1007/978-3-642-15561-1_16'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_16'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_16'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_16'


 

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

137 TRIPLES      22 PREDICATES      72 URIs      65 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-15561-1_16 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ndee2efd283934cb7a06b37c9a3423106
4 schema:datePublished 2010
5 schema:datePublishedReg 2010-01-01
6 schema:description Domain adaptation is an important emerging topic in computer vision. In this paper, we present one of the first studies of domain shift in the context of object recognition. We introduce a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. The transformation is learned in a supervised manner and can be applied to categories for which there are no labeled examples in the new domain. While we focus our evaluation on object recognition tasks, the transform-based adaptation technique we develop is general and could be applied to non-image data. Another contribution is a new multi-domain object database, freely available for download. We experimentally demonstrate the ability of our method to improve recognition on categories with few or no target domain labels and moderate to large changes in the imaging conditions.
7 schema:editor N846959abdb544568ab8f71e8c2b293ca
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf Nff52bbb7eea34481b01c8e3f27d44dca
11 schema:keywords ability
12 adaptation
13 adaptation techniques
14 categories
15 category model
16 changes
17 computer vision
18 conditions
19 context
20 contribution
21 data
22 database
23 distribution
24 domain
25 domain adaptation
26 domain labels
27 domain shift
28 download
29 effect
30 evaluation
31 example
32 feature distribution
33 first study
34 labels
35 large changes
36 manner
37 method
38 model
39 new domain
40 non-image data
41 object databases
42 object model
43 object recognition
44 object recognition task
45 paper
46 recognition
47 recognition task
48 shift
49 study
50 supervised manner
51 target domain labels
52 task
53 technique
54 topic
55 transformation
56 vision
57 visual domain
58 schema:name Adapting Visual Category Models to New Domains
59 schema:pagination 213-226
60 schema:productId Nb7fb0f7169ae486894f437c7a0d5ce1c
61 Nead6a11ca18146a68149df10d8a08449
62 schema:publisher N4b58835478754b098f75a5db49200b85
63 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047848527
64 https://doi.org/10.1007/978-3-642-15561-1_16
65 schema:sdDatePublished 2022-12-01T06:54
66 schema:sdLicense https://scigraph.springernature.com/explorer/license/
67 schema:sdPublisher N155b9626c401421a9cd31f25e5fbf2e6
68 schema:url https://doi.org/10.1007/978-3-642-15561-1_16
69 sgo:license sg:explorer/license/
70 sgo:sdDataset chapters
71 rdf:type schema:Chapter
72 N155b9626c401421a9cd31f25e5fbf2e6 schema:name Springer Nature - SN SciGraph project
73 rdf:type schema:Organization
74 N16b9004915a049a9b452f7e6f3042583 rdf:first Nab4111ef20fa4760b6cef84fcc0b1f22
75 rdf:rest rdf:nil
76 N27d1bb352acf4194a898400c2f3f7566 rdf:first sg:person.01046073067.44
77 rdf:rest N9be8247b1d054927bf8d5eb80406d3ff
78 N4b58835478754b098f75a5db49200b85 schema:name Springer Nature
79 rdf:type schema:Organisation
80 N7f5c4ebf65de46a69fa06c720932a414 schema:familyName Maragos
81 schema:givenName Petros
82 rdf:type schema:Person
83 N7fa5bcf7837a4ac0afb743210767ece8 schema:familyName Daniilidis
84 schema:givenName Kostas
85 rdf:type schema:Person
86 N846959abdb544568ab8f71e8c2b293ca rdf:first N7fa5bcf7837a4ac0afb743210767ece8
87 rdf:rest Nf15aecb334d64c999fe5fd2e036d62fe
88 N9be8247b1d054927bf8d5eb80406d3ff rdf:first sg:person.013361072755.17
89 rdf:rest N9f5377419088408188442dde041a87b9
90 N9f5377419088408188442dde041a87b9 rdf:first sg:person.01001613660.25
91 rdf:rest rdf:nil
92 Nab4111ef20fa4760b6cef84fcc0b1f22 schema:familyName Paragios
93 schema:givenName Nikos
94 rdf:type schema:Person
95 Nb7fb0f7169ae486894f437c7a0d5ce1c schema:name doi
96 schema:value 10.1007/978-3-642-15561-1_16
97 rdf:type schema:PropertyValue
98 Ndee2efd283934cb7a06b37c9a3423106 rdf:first sg:person.0617252060.44
99 rdf:rest N27d1bb352acf4194a898400c2f3f7566
100 Nead6a11ca18146a68149df10d8a08449 schema:name dimensions_id
101 schema:value pub.1047848527
102 rdf:type schema:PropertyValue
103 Nf15aecb334d64c999fe5fd2e036d62fe rdf:first N7f5c4ebf65de46a69fa06c720932a414
104 rdf:rest N16b9004915a049a9b452f7e6f3042583
105 Nff52bbb7eea34481b01c8e3f27d44dca schema:isbn 978-3-642-15560-4
106 978-3-642-15561-1
107 schema:name Computer Vision – ECCV 2010
108 rdf:type schema:Book
109 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
110 schema:name Information and Computing Sciences
111 rdf:type schema:DefinedTerm
112 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
113 schema:name Artificial Intelligence and Image Processing
114 rdf:type schema:DefinedTerm
115 sg:person.01001613660.25 schema:affiliation grid-institutes:grid.47840.3f
116 schema:familyName Darrell
117 schema:givenName Trevor
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01001613660.25
119 rdf:type schema:Person
120 sg:person.01046073067.44 schema:affiliation grid-institutes:grid.47840.3f
121 schema:familyName Kulis
122 schema:givenName Brian
123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01046073067.44
124 rdf:type schema:Person
125 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.47840.3f
126 schema:familyName Fritz
127 schema:givenName Mario
128 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
129 rdf:type schema:Person
130 sg:person.0617252060.44 schema:affiliation grid-institutes:grid.47840.3f
131 schema:familyName Saenko
132 schema:givenName Kate
133 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0617252060.44
134 rdf:type schema:Person
135 grid-institutes:grid.47840.3f schema:alternateName UC Berkeley EECS and ICSI, Berkeley, CA
136 schema:name UC Berkeley EECS and ICSI, Berkeley, CA
137 rdf:type schema:Organization
 




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


...