Revisiting the Fisher vector for fine-grained classification - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2014

Revisiting the Fisher vector for fine-grained classification

Résumé

This paper describes the joint submission of Inria and Xerox to their joint participation to the FGCOMP'2013 challenge. Although the proposed system follows most of the standard Fisher classification pipeline, we describe a few key features and good practices that significantly improve the accuracy when specifically considering fine-grain classification tasks. In particular, we consider the late fusion of two systems both based on Fisher vectors, but for which we choose drastically design choices that make them very complementary. Moreover, we propose a simple yet effective filtering strategy, which significantly boosts the performance for several class domains.
Fichier principal
Vignette du fichier
gosselin14prl.pdf (2.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01056223 , version 1 (18-08-2014)

Identifiants

  • HAL Id : hal-01056223 , version 1

Citer

Philippe-Henri Gosselin, Naila Murray, Hervé Jégou, Florent Perronnin. Revisiting the Fisher vector for fine-grained classification. Pattern Recognition Letters, 2014, 49, pp.92-98. ⟨hal-01056223⟩
525 Consultations
1368 Téléchargements

Partager

Gmail Facebook X LinkedIn More