Approximate Fisher Kernels of non-iid Image Models for Image Categorization

Ramazan Gokberk Cinbis 1, 2 Jakob Verbeek 3, 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : The bag-of-words (BoW) model treats images as sets of local descriptors and represents them by visual word histograms. The Fisher vector (FV) representation extends BoW, by considering the first and second order statistics of local descriptors. In both representations local descriptors are assumed to be identically and independently distributed (iid), which is a poor assumption from a modeling perspective. It has been experimentally observed that the performance of BoW and FV representations can be improved by employing discounting transformations such as power normalization. In this paper, we introduce non-iid models by treating the model parameters as latent variables which are integrated out, rendering all local regions dependent. Using the Fisher kernel principle we encode an image by the gradient of the data log-likelihood w.r.t. the model hyper-parameters. Our models naturally generate discounting effects in the representations; suggesting that such transformations have proven successful because they closely correspond to the representations obtained for non-iid models. To enable tractable computation, we rely on variational free-energy bounds to learn the hyper-parameters and to compute approximate Fisher kernels. Our experimental evaluation results validate that our models lead to performance improvements comparable to using power normalization, as employed in state-of-the-art feature aggregation methods.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 38 (6), pp.1084-1098. <10.1109/TPAMI.2015.2484342>
Liste complète des métadonnées



https://hal.inria.fr/hal-01211201
Contributeur : Thoth Team <>
Soumis le : mardi 6 octobre 2015 - 23:01:33
Dernière modification le : mardi 19 juillet 2016 - 13:38:07
Document(s) archivé(s) le : jeudi 7 janvier 2016 - 10:15:03

Fichiers

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Approximate Fisher Kernels of non-iid Image Models for Image Categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 38 (6), pp.1084-1098. <10.1109/TPAMI.2015.2484342>. <hal-01211201>

Partager

Métriques

Consultations de
la notice

646

Téléchargements du document

312