Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018-10-06

AUTHORS

Yang He , Bernt Schiele , Mario Fritz

ABSTRACT

Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning procedure, but still suffer from stability issues. On the other hand, Conditional Variational Auto-Encoders (CVAE) models provide a sound way of conditional modeling but suffer from mode-mixing issues. Therefore, recent work has turned back to simple and stable regression models that are effective at generation but give up on the sampling mechanism and the latent code representation. We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research. In addition, a new training objective increases coverage of the training distribution leading to improvements over the state of the art in terms of accuracy as well as diversity. More... »

PAGES

422-437

Book

TITLE

Computer Vision – ECCV 2018

ISBN

978-3-030-01269-4
978-3-030-01270-0

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-01270-0_25

DOI

http://dx.doi.org/10.1007/978-3-030-01270-0_25

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1107454831


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/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarland Informatics Campus, 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": "Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarland Informatics Campus, 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, Saarland Informatics Campus, Saarbr\u00fccken, Germany", 
          "id": "http://www.grid.ac/institutes/grid.419528.3", 
          "name": [
            "Max Planck Institute for Informatics, Saarland Informatics Campus, 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": "2018-10-06", 
    "datePublishedReg": "2018-10-06", 
    "description": "Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning procedure, but still suffer from stability issues. On the other hand, Conditional Variational Auto-Encoders (CVAE) models provide a sound way of conditional modeling but suffer from mode-mixing issues. Therefore, recent work has turned back to simple and stable regression models that are effective at generation but give up on the sampling mechanism and the latent code representation. We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research. In addition, a new training objective increases coverage of the training distribution leading to improvements over the state of the art in terms of accuracy as well as diversity.", 
    "editor": [
      {
        "familyName": "Ferrari", 
        "givenName": "Vittorio", 
        "type": "Person"
      }, 
      {
        "familyName": "Hebert", 
        "givenName": "Martial", 
        "type": "Person"
      }, 
      {
        "familyName": "Sminchisescu", 
        "givenName": "Cristian", 
        "type": "Person"
      }, 
      {
        "familyName": "Weiss", 
        "givenName": "Yair", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-01270-0_25", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-030-01269-4", 
        "978-3-030-01270-0"
      ], 
      "name": "Computer Vision \u2013 ECCV 2018", 
      "type": "Book"
    }, 
    "keywords": [
      "generative adversarial network", 
      "variational auto-encoder model", 
      "conditional image generation", 
      "auto-encoder model", 
      "terms of accuracy", 
      "deep learning", 
      "adversarial network", 
      "code representation", 
      "image generation", 
      "stable regression model", 
      "training distribution", 
      "generative model", 
      "learning procedure", 
      "sampling mechanism", 
      "probabilistic modeling", 
      "sound way", 
      "conditional modeling", 
      "code", 
      "line of research", 
      "network", 
      "regression approach", 
      "learning", 
      "recent work", 
      "modeling", 
      "images", 
      "issues", 
      "accuracy", 
      "representation", 
      "model", 
      "recent advances", 
      "stochastic regression", 
      "art", 
      "generation", 
      "strong improvement", 
      "stability issues", 
      "improvement", 
      "hand", 
      "way", 
      "work", 
      "advances", 
      "coverage", 
      "research", 
      "merits", 
      "terms", 
      "state", 
      "regression models", 
      "regression", 
      "procedure", 
      "diversity", 
      "addition", 
      "mechanism", 
      "lines", 
      "distribution", 
      "drop", 
      "approach"
    ], 
    "name": "Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes", 
    "pagination": "422-437", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1107454831"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-01270-0_25"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-01270-0_25", 
      "https://app.dimensions.ai/details/publication/pub.1107454831"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:49", 
    "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_263.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-01270-0_25"
  }
]
 

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.10.1007/978-3-030-01270-0_25'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01270-0_25'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01270-0_25'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01270-0_25'


 

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

143 TRIPLES      22 PREDICATES      79 URIs      72 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-01270-0_25 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N4f90825b936a4b7fb1a9edafb38bd104
4 schema:datePublished 2018-10-06
5 schema:datePublishedReg 2018-10-06
6 schema:description Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning procedure, but still suffer from stability issues. On the other hand, Conditional Variational Auto-Encoders (CVAE) models provide a sound way of conditional modeling but suffer from mode-mixing issues. Therefore, recent work has turned back to simple and stable regression models that are effective at generation but give up on the sampling mechanism and the latent code representation. We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research. In addition, a new training objective increases coverage of the training distribution leading to improvements over the state of the art in terms of accuracy as well as diversity.
7 schema:editor N7a8879138a7c4cf1894a4a92d09b1c93
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N41eb2e9239264bd28427a0eb294e495f
11 schema:keywords accuracy
12 addition
13 advances
14 adversarial network
15 approach
16 art
17 auto-encoder model
18 code
19 code representation
20 conditional image generation
21 conditional modeling
22 coverage
23 deep learning
24 distribution
25 diversity
26 drop
27 generation
28 generative adversarial network
29 generative model
30 hand
31 image generation
32 images
33 improvement
34 issues
35 learning
36 learning procedure
37 line of research
38 lines
39 mechanism
40 merits
41 model
42 modeling
43 network
44 probabilistic modeling
45 procedure
46 recent advances
47 recent work
48 regression
49 regression approach
50 regression models
51 representation
52 research
53 sampling mechanism
54 sound way
55 stability issues
56 stable regression model
57 state
58 stochastic regression
59 strong improvement
60 terms
61 terms of accuracy
62 training distribution
63 variational auto-encoder model
64 way
65 work
66 schema:name Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes
67 schema:pagination 422-437
68 schema:productId N3a529f8ee9ab4edb87517921d25f2fce
69 N8b347b6b23d2498da1a9ce6d93d901b3
70 schema:publisher N2bda5fb46d04440fa5fea8032b7ef81b
71 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454831
72 https://doi.org/10.1007/978-3-030-01270-0_25
73 schema:sdDatePublished 2022-12-01T06:49
74 schema:sdLicense https://scigraph.springernature.com/explorer/license/
75 schema:sdPublisher N1554d78812734f4bb930adc510fefab8
76 schema:url https://doi.org/10.1007/978-3-030-01270-0_25
77 sgo:license sg:explorer/license/
78 sgo:sdDataset chapters
79 rdf:type schema:Chapter
80 N1554d78812734f4bb930adc510fefab8 schema:name Springer Nature - SN SciGraph project
81 rdf:type schema:Organization
82 N191eb612adae46c4a512c127cdfc73a4 rdf:first Nabf2e94bc3144493ae0c42837d677d1d
83 rdf:rest Nfd3f7513d9664c1fa65834c78d595ec7
84 N2bda5fb46d04440fa5fea8032b7ef81b schema:name Springer Nature
85 rdf:type schema:Organisation
86 N3a529f8ee9ab4edb87517921d25f2fce schema:name doi
87 schema:value 10.1007/978-3-030-01270-0_25
88 rdf:type schema:PropertyValue
89 N41eb2e9239264bd28427a0eb294e495f schema:isbn 978-3-030-01269-4
90 978-3-030-01270-0
91 schema:name Computer Vision – ECCV 2018
92 rdf:type schema:Book
93 N4f90825b936a4b7fb1a9edafb38bd104 rdf:first sg:person.010655401332.41
94 rdf:rest N5e0a511b30dd4ff3bcd2f7098793fa00
95 N5c65bc7972f4424cb89e211dd2fb3bdc schema:familyName Hebert
96 schema:givenName Martial
97 rdf:type schema:Person
98 N5e0a511b30dd4ff3bcd2f7098793fa00 rdf:first sg:person.01174260421.90
99 rdf:rest Nb08d84f651d84a75895b2d0a34619e16
100 N7a8879138a7c4cf1894a4a92d09b1c93 rdf:first Nd63426f445724b23b549d50490da8718
101 rdf:rest Na88b5e56b76d4d71a1737c6b4a7ca850
102 N8b347b6b23d2498da1a9ce6d93d901b3 schema:name dimensions_id
103 schema:value pub.1107454831
104 rdf:type schema:PropertyValue
105 Na88b5e56b76d4d71a1737c6b4a7ca850 rdf:first N5c65bc7972f4424cb89e211dd2fb3bdc
106 rdf:rest N191eb612adae46c4a512c127cdfc73a4
107 Nabf2e94bc3144493ae0c42837d677d1d schema:familyName Sminchisescu
108 schema:givenName Cristian
109 rdf:type schema:Person
110 Nb08d84f651d84a75895b2d0a34619e16 rdf:first sg:person.013361072755.17
111 rdf:rest rdf:nil
112 Nd4f5248c72334cee876c37204910cabf schema:familyName Weiss
113 schema:givenName Yair
114 rdf:type schema:Person
115 Nd63426f445724b23b549d50490da8718 schema:familyName Ferrari
116 schema:givenName Vittorio
117 rdf:type schema:Person
118 Nfd3f7513d9664c1fa65834c78d595ec7 rdf:first Nd4f5248c72334cee876c37204910cabf
119 rdf:rest rdf:nil
120 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
121 schema:name Mathematical Sciences
122 rdf:type schema:DefinedTerm
123 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
124 schema:name Statistics
125 rdf:type schema:DefinedTerm
126 sg:person.010655401332.41 schema:affiliation grid-institutes:grid.419528.3
127 schema:familyName He
128 schema:givenName Yang
129 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010655401332.41
130 rdf:type schema:Person
131 sg:person.01174260421.90 schema:affiliation grid-institutes:grid.419528.3
132 schema:familyName Schiele
133 schema:givenName Bernt
134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01174260421.90
135 rdf:type schema:Person
136 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.419528.3
137 schema:familyName Fritz
138 schema:givenName Mario
139 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
140 rdf:type schema:Person
141 grid-institutes:grid.419528.3 schema:alternateName Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany
142 schema:name Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany
143 rdf:type schema:Organization
 




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


...