Ontology type: schema:Chapter
2017-05-10
AUTHORSChristin Seifert , Aisha Aamir , Aparna Balagopalan , Dhruv Jain , Abhinav Sharma , Sebastian Grottel , Stefan Gumhold
ABSTRACTIn recent years, Deep Neural Networks (DNNs) have been shown to outperform the state-of-the-art in multiple areas, such as visual object recognition, genomics and speech recognition. Due to the distributed encodings of information, DNNs are hard to understand and interpret. To this end, visualizations have been used to understand how deep architecture work in general, what different layers of the network encode, what the limitations of the trained model was and how to interactively collect user feedback. In this chapter, we provide a survey of visualizations of DNNs in the field of computer vision. We define a classification scheme describing visualization goals and methods as well as the application areas. This survey gives an overview of what can be learned from visualizing DNNs and which visualization methods were used to gain which insights. We found that most papers use Pixel Displays to show neuron activations. However, recently more sophisticated visualizations like interactive node-link diagrams were proposed. The presented overview can serve as a guideline when applying visualizations while designing DNNs. More... »
PAGES123-144
Transparent Data Mining for Big and Small Data
ISBN
978-3-319-54023-8
978-3-319-54024-5
http://scigraph.springernature.com/pub.10.1007/978-3-319-54024-5_6
DOIhttp://dx.doi.org/10.1007/978-3-319-54024-5_6
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1085381604
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": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Seifert",
"givenName": "Christin",
"id": "sg:person.010257616672.34",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Aamir",
"givenName": "Aisha",
"id": "sg:person.012207204401.97",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012207204401.97"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Balagopalan",
"givenName": "Aparna",
"id": "sg:person.014377526001.80",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014377526001.80"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Jain",
"givenName": "Dhruv",
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Sharma",
"givenName": "Abhinav",
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Grottel",
"givenName": "Sebastian",
"id": "sg:person.01146556151.00",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01146556151.00"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Dresden, Dresden, Germany",
"id": "http://www.grid.ac/institutes/grid.4488.0",
"name": [
"Technische Universit\u00e4t Dresden, Dresden, Germany"
],
"type": "Organization"
},
"familyName": "Gumhold",
"givenName": "Stefan",
"id": "sg:person.011202146505.82",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011202146505.82"
],
"type": "Person"
}
],
"datePublished": "2017-05-10",
"datePublishedReg": "2017-05-10",
"description": "In recent years, Deep Neural Networks (DNNs) have been shown to outperform the state-of-the-art in multiple areas, such as visual object recognition, genomics and speech recognition. Due to the distributed encodings of information, DNNs are hard to understand and interpret. To this end, visualizations have been used to understand how deep architecture work in general, what different layers of the network encode, what the limitations of the trained model was and how to interactively collect user feedback. In this chapter, we provide a survey of visualizations of DNNs in the field of computer vision. We define a classification scheme describing visualization goals and methods as well as the application areas. This survey gives an overview of what can be learned from visualizing DNNs and which visualization methods were used to gain which insights. We found that most papers use Pixel Displays to show neuron activations. However, recently more sophisticated visualizations like interactive node-link diagrams were proposed. The presented overview can serve as a guideline when applying visualizations while designing DNNs.",
"editor": [
{
"familyName": "Cerquitelli",
"givenName": "Tania",
"type": "Person"
},
{
"familyName": "Quercia",
"givenName": "Daniele",
"type": "Person"
},
{
"familyName": "Pasquale",
"givenName": "Frank",
"type": "Person"
}
],
"genre": "chapter",
"id": "sg:pub.10.1007/978-3-319-54024-5_6",
"inLanguage": "en",
"isAccessibleForFree": false,
"isPartOf": {
"isbn": [
"978-3-319-54023-8",
"978-3-319-54024-5"
],
"name": "Transparent Data Mining for Big and Small Data",
"type": "Book"
},
"keywords": [
"deep neural networks",
"computer vision",
"neural network",
"survey of visualization",
"node-link diagrams",
"visualization goals",
"sophisticated visualization",
"visual object recognition",
"user feedback",
"speech recognition",
"object recognition",
"architecture work",
"application areas",
"visualization method",
"network",
"visualization",
"different layers",
"classification scheme",
"pixel display",
"vision",
"recognition",
"neuron activation",
"recent years",
"encoding",
"scheme",
"presented overview",
"information",
"most papers",
"multiple areas",
"display",
"overview",
"art",
"feedback",
"method",
"goal",
"work",
"limitations",
"model",
"area",
"encoding of information",
"diagram",
"field",
"end",
"survey",
"state",
"chapter",
"layer",
"genomics",
"insights",
"guidelines",
"years",
"paper",
"activation"
],
"name": "Visualizations of Deep Neural Networks in Computer Vision: A Survey",
"pagination": "123-144",
"productId": [
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1085381604"
]
},
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/978-3-319-54024-5_6"
]
}
],
"publisher": {
"name": "Springer Nature",
"type": "Organisation"
},
"sameAs": [
"https://doi.org/10.1007/978-3-319-54024-5_6",
"https://app.dimensions.ai/details/publication/pub.1085381604"
],
"sdDataset": "chapters",
"sdDatePublished": "2022-06-01T22:34",
"sdLicense": "https://scigraph.springernature.com/explorer/license/",
"sdPublisher": {
"name": "Springer Nature - SN SciGraph project",
"type": "Organization"
},
"sdSource": "s3://com-springernature-scigraph/baseset/20220601/entities/gbq_results/chapter/chapter_423.jsonl",
"type": "Chapter",
"url": "https://doi.org/10.1007/978-3-319-54024-5_6"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
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.10.1007/978-3-319-54024-5_6'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-54024-5_6'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-54024-5_6'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-54024-5_6'
This table displays all metadata directly associated to this object as RDF triples.
163 TRIPLES
23 PREDICATES
77 URIs
70 LITERALS
7 BLANK NODES