Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Milbich, Timo [VerfasserIn]   i
 Ghori, Omair [VerfasserIn]   i
 Diego, Ferran [VerfasserIn]   i
 Ommer, Björn [VerfasserIn]   i
Titel:Unsupervised representation learning by discovering reliable image relations
Verf.angabe:Timo Milbich, Omair Ghori, Ferran Diego, Björn Ommer
E-Jahr:2020
Jahr:17 January 2020
Fussnoten:Gesehen am 16.12.2020
Titel Quelle:Enthalten in: Pattern recognition
Ort Quelle:Amsterdam : Elsevier, 1968
Jahr Quelle:2020
Band/Heft Quelle:102(2020) Artikel-Nummer 107107, 11 Seiten
Abstract:Learning robust representations that allow to reliably establish relations between images is of paramount importance for virtually all of computer vision. Annotating the quadratic number of pairwise relations between training images is simply not feasible, while unsupervised inference is prone to noise, thus leaving the vast majority of these relations to be unreliable. To nevertheless find those relations which can be reliably utilized for learning, we follow a divide-and-conquer strategy: We find reliable similarities by extracting compact groups of images and reliable dissimilarities by partitioning these groups into subsets, converting the complicated overall problem into few reliable local subproblems. For each of the subsets we obtain a representation by learning a mapping to a target feature space so that their reliable relations are kept. Transitivity relations between the subsets are then exploited to consolidate the local solutions into a concerted global representation. While iterating between grouping, partitioning, and learning, we can successively use more and more reliable relations which, in turn, improves our image representation. In experiments, our approach shows state-of-the-art performance on unsupervised classification on ImageNet with 46.0% and competes favorably on different transfer learning tasks on PASCAL VOC.
DOI:doi:10.1016/j.patcog.2019.107107
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

Volltext ; Verlag: https://doi.org/10.1016/j.patcog.2019.107107
 Volltext: http://www.sciencedirect.com/science/article/pii/S003132031930408X
 DOI: https://doi.org/10.1016/j.patcog.2019.107107
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:Divide-and-conquer
 Mining reliable relations
 Unsupervised image classification
 Unsupervised learning
 Visual representation learning
K10plus-PPN:1743040296
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/68673910   QR-Code
zum Seitenanfang