Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Zero-Shot Learning with Structured Embeddings

Akata, Z., Lee, H., & Schiele, B. (2014). Zero-Shot Learning with Structured Embeddings. Retrieved from http://arxiv.org/abs/1409.8403.

Item is

Dateien

einblenden: Dateien
ausblenden: Dateien
:
arXiv:1409.8403.pdf (Preprint), 281KB
Name:
arXiv:1409.8403.pdf
Beschreibung:
File downloaded from arXiv at 2014-12-02 16:30
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Akata, Zeynep1, Autor           
Lee, Honglak2, Autor
Schiele, Bernt1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Zusammenfassung: Despite significant recent advances in image classification, fine-grained classification remains a challenge. In the present paper, we address the zero-shot and few-shot learning scenarios as obtaining labeled data is especially difficult for fine-grained classification tasks. First, we embed state-of-the-art image descriptors in a label embedding space using side information such as attributes. We argue that learning a joint embedding space, that maximizes the compatibility between the input and output embeddings, is highly effective for zero/few-shot learning. We show empirically that such embeddings significantly outperforms the current state-of-the-art methods on two challenging datasets (Caltech-UCSD Birds and Animals with Attributes). Second, to reduce the amount of costly manual attribute annotations, we use alternate output embeddings based on the word-vector representations, obtained from large text-corpora without any supervision. We report that such unsupervised embeddings achieve encouraging results, and lead to further improvements when combined with the supervised ones.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2014-09-302014
 Publikationsstatus: Online veröffentlicht
 Seiten: 10 p.
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: arXiv: 1409.8403
URI: http://arxiv.org/abs/1409.8403
BibTex Citekey: Akata2014arXiv
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: