Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Transfer Learning in a Transductive Setting

Rohrbach, M., Ebert, S., & Schiele, B. (2013). Transfer Learning in a Transductive Setting. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 26 (pp. 46-54). Red Hook, NY: Curran.

Item is

Externe Referenzen

einblenden:
ausblenden:
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Rohrbach, Marcus1, Autor           
Ebert, Sandra1, Autor           
Schiele, Bernt1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Category models for objects or activities typically rely on supervised learning requiring sufficiently large training sets. Transferring knowledge from known categories to novel classes with no or only a few labels however is far less researched even though it is a common scenario. In this work, we extend transfer learning with semi-supervised learning to exploit unlabeled instances of (novel) categories with no or only a few labeled instances. Our proposed approach Propagated Semantic Transfer combines three main ingredients. First, we transfer information from known to novel categories by incorporating external knowledge, such as linguistic or expert-specified information, e.g., by a mid-level layer of semantic attributes. Second, we exploit the manifold structure of novel classes. More specifically we adapt a graph-based learning algorithm - so far only used for semi-supervised learning - to zero-shot and few-shot learning. Third, we improve the local neighborhood in such graph structures by replacing the raw feature-based representation with a mid-level object- or attribute-based representation. We evaluate our approach on three challenging datasets in two different applications, namely on Animals with Attributes and ImageNet for image classification and on MPII Composites for activity recognition. Our approach consistently outperforms state-of-the-art transfer and semi-supervised approaches on all datasets.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20132013
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eSciDoc: escidoc:1835345
BibTex Citekey: escidoc:1835345
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 27th Annual Conference on Neural Information Processing Systems
Veranstaltungsort: Lake Tahoe, NV, USA
Start-/Enddatum: 2013-12-05 - 2013-12-10

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Advances in Neural Information Processing Systems 26
  Kurztitel : NIPS 2013
Genre der Quelle: Konferenzband
 Urheber:
Burges, C. J. C.1, Herausgeber
Bottou, L.1, Herausgeber
Welling, M.1, Herausgeber
Ghahramani, Z.1, Herausgeber
Weinberger, K. Q.1, Herausgeber
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Red Hook, NY : Curran
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 46 - 54 Identifikator: ISBN: 978-1-63266-024-4