A comparison of dense region detectors for image search and fine-grained classification

Abstract : We consider a pipeline for image classification or search based on coding approaches like Bag of Words or Fisher vectors. In this context, the most common approach is to extract the image patches regularly in a dense manner on several scales. This paper proposes and evaluates alternative choices to extract patches densely. Beyond simple strategies derived from regular interest region detectors, we propose approaches based on super-pixels, edges, and a bank of Zernike filters used as detectors. The different approaches are evaluated on recent image retrieval and fine-grain classification benchmarks. Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks. As a byproduct of our study, we show that existing methods for blob and super-pixel extraction achieve high accuracy if the patches are extracted along the edges and not around the detected regions.
Type de document :
Article dans une revue
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2015, pp.00. <10.1109/TIP.2015.2423557>
Liste complète des métadonnées


https://hal.inria.fr/hal-01143201
Contributeur : Ahmet Iscen <>
Soumis le : jeudi 16 avril 2015 - 22:33:00
Dernière modification le : vendredi 17 février 2017 - 16:11:34
Document(s) archivé(s) le : mardi 18 avril 2017 - 22:38:19

Fichier

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

Identifiants

Citation

Ahmet Iscen, Giorgos Tolias, Philippe-Henri Gosselin, Hervé Jégou. A comparison of dense region detectors for image search and fine-grained classification. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2015, pp.00. <10.1109/TIP.2015.2423557>. <hal-01143201>

Partager

Métriques

Consultations de
la notice

541

Téléchargements du document

342