Inria+Xerox@FGcomp: Boosting the Fisher vector for fine-grained classification - Inria - Institut national de recherche en sciences et technologies du numérique
Rapport (Rapport De Recherche) Année : 2013

Inria+Xerox@FGcomp: Boosting the Fisher vector for fine-grained classification

Résumé

This report describes the joint submission of Inria and Xerox to their participation to the FGCOMP 2013 challenge. Although the proposed system follows most of the standard Fisher classification pipeline, we describe several key features and good practices that improve the accuracy when specifically considering fine-grained classification tasks. In particular, we consider the late fusion of two systems both based on Fisher vectors, but that employ drastically different design choices that make them very complementary. Moreover, we show that a simple yet effective filtering strategy significantly boosts the performance for several class domains.
Fichier principal
Vignette du fichier
RR-8431.pdf (2.1 Mo) Télécharger le fichier
Vignette du fichier
thumb.png (42.3 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Format Figure, Image
Loading...

Dates et versions

hal-00920187 , version 1 (18-12-2013)
hal-00920187 , version 2 (30-01-2014)

Identifiants

  • HAL Id : hal-00920187 , version 2

Citer

Philippe-Henri Gosselin, Naila Murray, Hervé Jégou, Florent Perronnin. Inria+Xerox@FGcomp: Boosting the Fisher vector for fine-grained classification. [Research Report] RR-8431, INRIA. 2013. ⟨hal-00920187v2⟩
913 Consultations
973 Téléchargements

Partager

More