Image categorization using Fisher kernels of non-iid image models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Image categorization using Fisher kernels of non-iid image models

Ramazan Gokberk Cinbis
  • Function : Author
  • PersonId : 933132
Jakob Verbeek
Cordelia Schmid
  • Function : Author
  • PersonId : 831154


The bag-of-words (BoW) model treats images as an unordered set of local regions and represents them by visual word histograms. Implicitly, regions are assumed to be identically and independently distributed (iid), which is a poor assumption from a modeling perspective. We introduce non-iid models by treating the parameters of BoW models as latent variables which are integrated out, rendering all local regions dependent. Using the Fisher kernel we encode an image by the gradient of the data log-likelihood w.r.t. hyper-parameters that control priors on the model parameters. Our representation naturally involves discounting transformations similar to taking square-roots, providing an explanation of why such transformations have proven successful. Using variational inference we extend the basic model to include Gaussian mixtures over local descriptors, and latent topic models to capture the co-occurrence structure of visual words, both improving performance. Our models yield state-of-the-art categorization performance using linear classifiers; without using non-linear transformations such as taking square-roots of features, or using (approximate) explicit embeddings of non-linear kernels.
Fichier principal
Vignette du fichier
paper_final.pdf (560.01 Ko) Télécharger le fichier
Vignette du fichier
fig1.jpg (29.81 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-00685943 , version 1 (06-04-2012)



Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Image categorization using Fisher kernels of non-iid image models. CVPR 2012 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2012, Providence, United States. pp.2184-2191, ⟨10.1109/CVPR.2012.6247926⟩. ⟨hal-00685943⟩
988 View
1967 Download



Gmail Facebook X LinkedIn More