Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  On Feature Combination for Multiclass Object Classification

Gehler, P., & Nowozin, S. (2009). On Feature Combination for Multiclass Object Classification. Proceedings of the Twelfth IEEE International Conference on Computer Vision (ICCV 2009), 221-228.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Gehler, PV1, Autor           
Nowozin, S1, Autor           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem due to the high variability of visual appearance within each class. In the last years substantial performance gains on challenging benchmark datasets have been reported in the literature. This progress can be attributed to two developments: the design of highly discriminative and robust image features and the combination of multiple complementary features based on different aspects such as shape, color or texture. In this paper we study several models that aim at learning the correct weighting of different features from training data. These include multiple kernel learning as well as simple baseline methods. Furthermore we derive ensemble methods inspired by Boosting which are easily extendable to several multiclass setting. All methods are thoroughly evaluated on object classification datasets using a multitude of feature descriptors. The key results are that even very simple baseline methods, that are orders of magnitude faster than learning techniques are highly competitive with multiple kernel learning. Furthermore the Boosting type methods are found to produce consistently better results in all experiments. We provide insight of when combination methods can be expected to work and how the benefit of complementary features can be exploited most efficiently.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2009-10
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://www.iccv2009.org/
DOI: 10.1109/ICCV.2009.5459169
BibTex Citekey: 5937
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Twelfth IEEE International Conference on Computer Vision
Veranstaltungsort: Kyoto, Japan
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Proceedings of the Twelfth IEEE International Conference on Computer Vision (ICCV 2009)
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ, USA : IEEE Computer Society
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 221 - 228 Identifikator: -