Image Classification with the Fisher Vector: Theory and Practice - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2013

Image Classification with the Fisher Vector: Theory and Practice


A standard approach to describe an image for classification and retrieval purposes is to extract a set of local patch descriptors, encode them into a high dimensional vector and pool them into an image-level signature. The most common patch encoding strategy consists in quantizing the local descriptors into a finite set of prototypical elements. This leads to the popular Bag-of-Visual words (BOV) representation. In this work, we propose to use the Fisher Kernel framework as an alternative patch encoding strategy: we describe patches by their deviation from an ''universal'' generative Gaussian mixture model. This representation, which we call Fisher Vector (FV) has many advantages: it is efficient to compute, it leads to excellent results even with efficient linear classifiers, and it can be compressed with a minimal loss of accuracy using product quantization. We report experimental results on five standard datasets -- PASCAL VOC 2007, Caltech 256, SUN 397, ILSVRC 2010 and ImageNet10K -- with up to 9M images and 10K classes, showing that the FV framework is a state-of-the-art patch encoding technique.
Fichier principal
Vignette du fichier
RR-8209.pdf (801.35 Ko) Télécharger le fichier
Vignette du fichier
Screenshot.png (61.93 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-00779493 , version 1 (22-01-2013)
hal-00779493 , version 2 (27-05-2013)
hal-00779493 , version 3 (12-06-2013)


  • HAL Id : hal-00779493 , version 3


Jorge Sanchez, Florent Perronnin, Thomas Mensink, Jakob Verbeek. Image Classification with the Fisher Vector: Theory and Practice. [Research Report] RR-8209, INRIA. 2013. ⟨hal-00779493v3⟩
2439 View
15034 Download


Gmail Facebook X LinkedIn More