Minimum Class Confusion for Versatile Domain Adaptation View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2020-11-12

AUTHORS

Ying Jin , Ximei Wang , Mingsheng Long , Jianmin Wang

ABSTRACT

There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing DA methods are generally designed only for a specific scenario, and may underperform for scenarios they are not tailored to. To this end, this paper studies Versatile Domain Adaptation (VDA), where one method can handle several different DA scenarios without any modification. Towards this goal, a more general inductive bias other than the domain alignment should be explored. We delve into a missing piece of existing methods: class confusion, the tendency that a classifier confuses the predictions between the correct and ambiguous classes for target examples, which is common in different DA scenarios. We uncover that reducing such pairwise class confusion leads to significant transfer gains. With this insight, we propose a general loss function: Minimum Class Confusion (MCC). It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7.3%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$7.3\%$$\end{document} on DomainNet). Its versatility is further justified by two scenarios proposed in this paper: Multi-Source Partial DA and Multi-Target Partial DA. In addition, it can also be used as a general regularizer that is orthogonal and complementary to a variety of existing DA methods, accelerating convergence and pushing these readily competitive methods to stronger ones. Code is available at https://github.com/thuml/Versatile-Domain-Adaptation. More... »

PAGES

464-480

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-58589-1_28

DOI

http://dx.doi.org/10.1007/978-3-030-58589-1_28

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1132537449


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": "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jin", 
        "givenName": "Ying", 
        "id": "sg:person.07422717707.09", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07422717707.09"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Ximei", 
        "id": "sg:person.014716677221.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014716677221.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Long", 
        "givenName": "Mingsheng", 
        "id": "sg:person.013417115303.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013417115303.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Jianmin", 
        "id": "sg:person.012303351315.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012303351315.43"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2020-11-12", 
    "datePublishedReg": "2020-11-12", 
    "description": "There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing DA methods are generally designed only for a specific scenario, and may underperform for scenarios they are not tailored to. To this end, this paper studies Versatile Domain Adaptation (VDA), where one method can handle several different DA scenarios without any modification. Towards this goal, a more general inductive bias other than the domain alignment should be explored. We delve into a missing piece of existing methods: class confusion, the tendency that a classifier confuses the predictions between the correct and ambiguous classes for target examples, which is common in different DA scenarios. We uncover that reducing such pairwise class confusion leads to significant transfer gains. With this insight, we propose a general loss function: Minimum Class Confusion (MCC). It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7.3%\\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym}\n\t\t\t\t\\usepackage{amsfonts}\n\t\t\t\t\\usepackage{amssymb}\n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$$7.3\\%$$\\end{document} on DomainNet). Its versatility is further justified by two scenarios proposed in this paper: Multi-Source Partial DA and Multi-Target Partial DA. In addition, it can also be used as a general regularizer that is orthogonal and complementary to a variety of existing DA methods, accelerating convergence and pushing these readily competitive methods to stronger ones. Code is available at https://github.com/thuml/Versatile-Domain-Adaptation.", 
    "editor": [
      {
        "familyName": "Vedaldi", 
        "givenName": "Andrea", 
        "type": "Person"
      }, 
      {
        "familyName": "Bischof", 
        "givenName": "Horst", 
        "type": "Person"
      }, 
      {
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "type": "Person"
      }, 
      {
        "familyName": "Frahm", 
        "givenName": "Jan-Michael", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-58589-1_28", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-030-58588-4", 
        "978-3-030-58589-1"
      ], 
      "name": "Computer Vision \u2013 ECCV 2020", 
      "type": "Book"
    }, 
    "keywords": [
      "domain adaptation", 
      "domain adaptation scenarios", 
      "label set", 
      "DA methods", 
      "DA scenarios", 
      "inductive bias", 
      "domain alignment", 
      "class confusion", 
      "faster convergence speed", 
      "art methods", 
      "hard datasets", 
      "adaptation scenarios", 
      "specific scenarios", 
      "target examples", 
      "loss function", 
      "convergence speed", 
      "Multi-Source", 
      "competitive methods", 
      "scenarios", 
      "ambiguous classes", 
      "general loss functions", 
      "partial set", 
      "set", 
      "classifier", 
      "dataset", 
      "regularizer", 
      "method", 
      "alignment", 
      "code", 
      "variety", 
      "adaptation", 
      "goal", 
      "example", 
      "speed", 
      "convergence", 
      "configuration", 
      "end", 
      "pieces", 
      "confusion", 
      "prediction", 
      "class", 
      "versatility", 
      "strong ones", 
      "one", 
      "gain", 
      "insights", 
      "function", 
      "versatile approach", 
      "state", 
      "DA", 
      "modification", 
      "date", 
      "addition", 
      "bias", 
      "tendency", 
      "transfer gain", 
      "approach", 
      "paper", 
      "partial-set DA", 
      "multi-target DA", 
      "Versatile Domain Adaptation", 
      "different DA scenarios", 
      "general inductive bias", 
      "such pairwise class confusion", 
      "pairwise class confusion", 
      "significant transfer gains", 
      "Minimum Class Confusion", 
      "non-adversarial DA method", 
      "Source Partial DA", 
      "Partial DA", 
      "Multi-Target Partial DA", 
      "general regularizer"
    ], 
    "name": "Minimum Class Confusion for Versatile Domain Adaptation", 
    "pagination": "464-480", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1132537449"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-58589-1_28"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-58589-1_28", 
      "https://app.dimensions.ai/details/publication/pub.1132537449"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:17", 
    "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/chapter/chapter_3.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-58589-1_28"
  }
]
 

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.10.1007/978-3-030-58589-1_28'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-58589-1_28'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-58589-1_28'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-58589-1_28'


 

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

168 TRIPLES      23 PREDICATES      97 URIs      90 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-58589-1_28 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N936749cac16546f3a54d7fabd19808f0
4 schema:datePublished 2020-11-12
5 schema:datePublishedReg 2020-11-12
6 schema:description There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing DA methods are generally designed only for a specific scenario, and may underperform for scenarios they are not tailored to. To this end, this paper studies Versatile Domain Adaptation (VDA), where one method can handle several different DA scenarios without any modification. Towards this goal, a more general inductive bias other than the domain alignment should be explored. We delve into a missing piece of existing methods: class confusion, the tendency that a classifier confuses the predictions between the correct and ambiguous classes for target examples, which is common in different DA scenarios. We uncover that reducing such pairwise class confusion leads to significant transfer gains. With this insight, we propose a general loss function: Minimum Class Confusion (MCC). It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7.3%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$7.3\%$$\end{document} on DomainNet). Its versatility is further justified by two scenarios proposed in this paper: Multi-Source Partial DA and Multi-Target Partial DA. In addition, it can also be used as a general regularizer that is orthogonal and complementary to a variety of existing DA methods, accelerating convergence and pushing these readily competitive methods to stronger ones. Code is available at https://github.com/thuml/Versatile-Domain-Adaptation.
7 schema:editor N9c8b243014c74427b458738b8403c140
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N8bddd58d7af142f29c09633867a1be4d
12 schema:keywords DA
13 DA methods
14 DA scenarios
15 Minimum Class Confusion
16 Multi-Source
17 Multi-Target Partial DA
18 Partial DA
19 Source Partial DA
20 Versatile Domain Adaptation
21 adaptation
22 adaptation scenarios
23 addition
24 alignment
25 ambiguous classes
26 approach
27 art methods
28 bias
29 class
30 class confusion
31 classifier
32 code
33 competitive methods
34 configuration
35 confusion
36 convergence
37 convergence speed
38 dataset
39 date
40 different DA scenarios
41 domain adaptation
42 domain adaptation scenarios
43 domain alignment
44 end
45 example
46 faster convergence speed
47 function
48 gain
49 general inductive bias
50 general loss functions
51 general regularizer
52 goal
53 hard datasets
54 inductive bias
55 insights
56 label set
57 loss function
58 method
59 modification
60 multi-target DA
61 non-adversarial DA method
62 one
63 pairwise class confusion
64 paper
65 partial set
66 partial-set DA
67 pieces
68 prediction
69 regularizer
70 scenarios
71 set
72 significant transfer gains
73 specific scenarios
74 speed
75 state
76 strong ones
77 such pairwise class confusion
78 target examples
79 tendency
80 transfer gain
81 variety
82 versatile approach
83 versatility
84 schema:name Minimum Class Confusion for Versatile Domain Adaptation
85 schema:pagination 464-480
86 schema:productId N10056f39111d45fea6ae9824d0095a76
87 N3ca0e10b065b466fa90a29ed3a3c21e3
88 schema:publisher Nde9c5404dc2d49679ad4744ee102a6f4
89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132537449
90 https://doi.org/10.1007/978-3-030-58589-1_28
91 schema:sdDatePublished 2022-01-01T19:17
92 schema:sdLicense https://scigraph.springernature.com/explorer/license/
93 schema:sdPublisher N90fd05c39c8946ef915e3f3f6d573fc5
94 schema:url https://doi.org/10.1007/978-3-030-58589-1_28
95 sgo:license sg:explorer/license/
96 sgo:sdDataset chapters
97 rdf:type schema:Chapter
98 N10056f39111d45fea6ae9824d0095a76 schema:name doi
99 schema:value 10.1007/978-3-030-58589-1_28
100 rdf:type schema:PropertyValue
101 N1d89e372e8174b67ab6020ebb2790a4c rdf:first sg:person.012303351315.43
102 rdf:rest rdf:nil
103 N3ca0e10b065b466fa90a29ed3a3c21e3 schema:name dimensions_id
104 schema:value pub.1132537449
105 rdf:type schema:PropertyValue
106 N5185bb3ab4a445fe9f7485d6231eb3b8 schema:familyName Bischof
107 schema:givenName Horst
108 rdf:type schema:Person
109 N7302da1ae0044d3fb56c8f410a41db99 schema:familyName Vedaldi
110 schema:givenName Andrea
111 rdf:type schema:Person
112 N8bddd58d7af142f29c09633867a1be4d schema:isbn 978-3-030-58588-4
113 978-3-030-58589-1
114 schema:name Computer Vision – ECCV 2020
115 rdf:type schema:Book
116 N90fd05c39c8946ef915e3f3f6d573fc5 schema:name Springer Nature - SN SciGraph project
117 rdf:type schema:Organization
118 N936749cac16546f3a54d7fabd19808f0 rdf:first sg:person.07422717707.09
119 rdf:rest Ne5318a2380fd4dcca7b65743aae6c6e9
120 N9c8b243014c74427b458738b8403c140 rdf:first N7302da1ae0044d3fb56c8f410a41db99
121 rdf:rest Ncbb368feef654cf2856169fc9bc36245
122 Na1ac5f85a3f045f9b48f1cb9c4d51687 rdf:first sg:person.013417115303.81
123 rdf:rest N1d89e372e8174b67ab6020ebb2790a4c
124 Na3c9193cc0aa4c08883a70702d6f32fa schema:familyName Brox
125 schema:givenName Thomas
126 rdf:type schema:Person
127 Nb5a2a94330e0443194be396f62c6a2b7 rdf:first Na3c9193cc0aa4c08883a70702d6f32fa
128 rdf:rest Nd0e06cf10006429b872729eb93169933
129 Ncbb368feef654cf2856169fc9bc36245 rdf:first N5185bb3ab4a445fe9f7485d6231eb3b8
130 rdf:rest Nb5a2a94330e0443194be396f62c6a2b7
131 Nd0e06cf10006429b872729eb93169933 rdf:first Ne5c67d3e966f4b118f2c26bfed4f4f52
132 rdf:rest rdf:nil
133 Nde9c5404dc2d49679ad4744ee102a6f4 schema:name Springer Nature
134 rdf:type schema:Organisation
135 Ne5318a2380fd4dcca7b65743aae6c6e9 rdf:first sg:person.014716677221.46
136 rdf:rest Na1ac5f85a3f045f9b48f1cb9c4d51687
137 Ne5c67d3e966f4b118f2c26bfed4f4f52 schema:familyName Frahm
138 schema:givenName Jan-Michael
139 rdf:type schema:Person
140 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
141 schema:name Information and Computing Sciences
142 rdf:type schema:DefinedTerm
143 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
144 schema:name Artificial Intelligence and Image Processing
145 rdf:type schema:DefinedTerm
146 sg:person.012303351315.43 schema:affiliation grid-institutes:grid.12527.33
147 schema:familyName Wang
148 schema:givenName Jianmin
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012303351315.43
150 rdf:type schema:Person
151 sg:person.013417115303.81 schema:affiliation grid-institutes:grid.12527.33
152 schema:familyName Long
153 schema:givenName Mingsheng
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013417115303.81
155 rdf:type schema:Person
156 sg:person.014716677221.46 schema:affiliation grid-institutes:grid.12527.33
157 schema:familyName Wang
158 schema:givenName Ximei
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014716677221.46
160 rdf:type schema:Person
161 sg:person.07422717707.09 schema:affiliation grid-institutes:grid.12527.33
162 schema:familyName Jin
163 schema:givenName Ying
164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07422717707.09
165 rdf:type schema:Person
166 grid-institutes:grid.12527.33 schema:alternateName School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China
167 schema:name School of Software, BNRist, Research Center for Big Data, Tsinghua University, Beijing, China
168 rdf:type schema:Organization
 




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


...