Image classification using object detectors - Archive ouverte HAL
Communication Dans Un Congrès ICIP 2013 : IEEE International Conference on Image Processing Année : 2013

Image classification using object detectors

Résumé

Image categorization is one of the most competitive topic in computer vision and image processing. In this paper, we propose to use trained object and region detectors to represent the visual content of each image. Compared to similar methods found in the literature, our method encompasses two main areas of novelty: introducing a new spatial pooling formalism and designing a late fusion strategy for combining our rep-resentation with state-of-the art methods based on low-level descriptors, e.g. Fisher Vectors and BossaNova. Our experiments carried out in the challenging PASCAL VOC 2007 dataset reveal outstanding performances. When combined with low-level representations, we reach more than 67.6% in MAP, outperforming recently reported results in this dataset with a large margin.
Fichier principal
Vignette du fichier
durand_icip2013.pdf (299.21 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01078079 , version 1 (27-10-2014)

Identifiants

Citer

Thibaut Durand, Nicolas Thome, Matthieu Cord, Sandra Avila. Image classification using object detectors. IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.4340 - 4344, ⟨10.1109/ICIP.2013.6738894⟩. ⟨hal-01078079⟩
151 Consultations
253 Téléchargements

Altmetric

Partager

More