Publikation: Decontextualized learning for interpretable hierarchical representations of visual patterns
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Apart from discriminative modeling, the application of deep convolutional neural networks to basic research utilizing natural imaging data faces unique hurdles. Here, we present decontextualized hierarchical representation learning (DHRL), designed specifically to overcome these limitations. DHRL enables the broader use of small datasets, which are typical in most studies. It also captures spatial relationships between features, provides novel tools for investigating latent variables, and achieves state-of-the-art disentanglement scores on small datasets. DHRL is enabled by a novel preprocessing technique inspired by generative model chaining and an improved ladder network architecture and regularization scheme. More than an analytical tool, DHRL enables novel capabilities for virtual experiments performed directly on a latent representation, which may transform the way we perform investigations of natural image features, directly integrating analytical, empirical, and theoretical approaches.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
ETHEREDGE, Robert Ian, Manfred SCHARTL, Alex JORDAN, 2021. Decontextualized learning for interpretable hierarchical representations of visual patterns. In: Patterns. Cell Press. 2021, 2(2), 100193. eISSN 2666-3899. Available under: doi: 10.1016/j.patter.2020.100193BibTex
@article{Etheredge2021-02Decon-52942, year={2021}, doi={10.1016/j.patter.2020.100193}, title={Decontextualized learning for interpretable hierarchical representations of visual patterns}, number={2}, volume={2}, journal={Patterns}, author={Etheredge, Robert Ian and Schartl, Manfred and Jordan, Alex}, note={Article Number: 100193} }
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52942"> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/> <dcterms:issued>2021-02</dcterms:issued> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-nd/4.0/"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/> <dc:contributor>Jordan, Alex</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/52942/1/Etheredge_2-1gmjjj99lu4t78.pdf"/> <dc:creator>Schartl, Manfred</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-02-19T12:58:16Z</dcterms:available> <dc:creator>Jordan, Alex</dc:creator> <dc:rights>Attribution-NonCommercial-NoDerivatives 4.0 International</dc:rights> <dc:language>eng</dc:language> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:abstract xml:lang="eng">Apart from discriminative modeling, the application of deep convolutional neural networks to basic research utilizing natural imaging data faces unique hurdles. Here, we present decontextualized hierarchical representation learning (DHRL), designed specifically to overcome these limitations. DHRL enables the broader use of small datasets, which are typical in most studies. It also captures spatial relationships between features, provides novel tools for investigating latent variables, and achieves state-of-the-art disentanglement scores on small datasets. DHRL is enabled by a novel preprocessing technique inspired by generative model chaining and an improved ladder network architecture and regularization scheme. More than an analytical tool, DHRL enables novel capabilities for virtual experiments performed directly on a latent representation, which may transform the way we perform investigations of natural image features, directly integrating analytical, empirical, and theoretical approaches.</dcterms:abstract> <dcterms:title>Decontextualized learning for interpretable hierarchical representations of visual patterns</dcterms:title> <dc:creator>Etheredge, Robert Ian</dc:creator> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/52942"/> <dc:contributor>Schartl, Manfred</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/52942/1/Etheredge_2-1gmjjj99lu4t78.pdf"/> <dc:contributor>Etheredge, Robert Ian</dc:contributor> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-02-19T12:58:16Z</dc:date> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/> </rdf:Description> </rdf:RDF>