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

Abstract : 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.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download


https://hal.inria.fr/hal-00920187
Contributor : Hervé Jégou <>
Submitted on : Thursday, January 30, 2014 - 10:51:02 AM
Last modification on : Tuesday, February 12, 2019 - 10:30:05 AM
Long-term archiving on : Sunday, April 9, 2017 - 2:50:49 AM

Files

RR-8431.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00920187, version 2

Citation

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⟩

Share

Metrics

Record views

1270

Files downloads

835