Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification

Abstract : This paper introduces a new image representation relying on the spatial pooling of geometrically consistent visual matches. We therefore introduce a new match kernel based on the in- verse rank of the shared nearest neighbors combined with local geometric constraints. To avoid over tting and reduce processing costs, the dimensionality of the resulting over- complete representation is further reduced by hierarchically pooling the raw consistent matches according to their spa- tial position in the training images. The nal image repre- sentation is obtained by concatenating the resulting feature vectors at several resolutions. Learning from these represen- tations using a logistic regression classi er is shown to pro- vide excellent ne-grained classi cation performances out- performing the results reported in the literature on several classi cation tasks.
Type de document :
Communication dans un congrès
International Conference on Multimedia Retrieval 2015, Jun 2015, Shangai, China
Liste complète des métadonnées

https://hal.inria.fr/hal-01145988
Contributeur : Alexis Joly <>
Soumis le : lundi 27 avril 2015 - 14:19:42
Dernière modification le : samedi 27 janvier 2018 - 01:31:45

Identifiants

  • HAL Id : hal-01145988, version 1

Collections

Citation

Valentin Leveau, Alexis Joly, Olivier Buisson, Patrick Valduriez. Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification. International Conference on Multimedia Retrieval 2015, Jun 2015, Shangai, China. 〈hal-01145988〉

Partager

Métriques

Consultations de la notice

502