Revisiting the Fisher vector for fine-grained classification

Philippe-Henri Gosselin 1, 2 Naila Murray 3 Hervé Jégou 1 Florent Perronnin 3
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 MIDI - Multimedia Indexation and Data Integration
ETIS - Equipes Traitement de l'Information et Systèmes
Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download
Contributor : Philippe-Henri Gosselin <>
Submitted on : Monday, August 18, 2014 - 11:20:14 AM
Last modification on : Friday, October 4, 2019 - 12:14:02 PM
Long-term archiving on : Thursday, November 27, 2014 - 2:00:22 AM


Files produced by the author(s)


  • HAL Id : hal-01056223, version 1


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



Record views


Files downloads