LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION

Abstract : In this work, we present an extended study of image representations for fine-grained classification with respect to image resolution. Understudied in literature, this parameter yet presents many practical and theoretical interests, e.g. in embedded systems where restricted computational resources prevent treating high-resolution images. It is thus interesting to figure out which representation provides the best results in this particular context. On this purpose, we evaluate Fisher Vectors and deep representations on two significant fine-grained oriented datasets: FGVC Aircraft and PPMI. We also introduce LR-CNN, a deep structure designed for classification of low-resolution images with strong semantic content. This net provides rich compact features and outperforms both pre-trained deep features and Fisher Vectors.
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing, Sep 2015, Québec city, Canada
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01196958
Contributeur : Marion Chevalier <>
Soumis le : jeudi 10 septembre 2015 - 16:55:50
Dernière modification le : samedi 24 novembre 2018 - 01:45:35
Document(s) archivé(s) le : mardi 29 décembre 2015 - 00:17:34

Fichier

Chevalier_ICIP15_LRCNNvaryingr...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01196958, version 1

Collections

Citation

Marion Chevalier, Nicolas Thome, Matthieu Cord, Jérôme Fournier, Gilles Henaff, et al.. LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION. IEEE International Conference on Image Processing, Sep 2015, Québec city, Canada. 〈hal-01196958〉

Partager

Métriques

Consultations de la notice

245

Téléchargements de fichiers

246