Image classification using object detectors

Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01078079
Contributor : Thibaut Durand <>
Submitted on : Monday, October 27, 2014 - 9:11:00 PM
Last modification on : Thursday, March 21, 2019 - 1:13:34 PM
Document(s) archivé(s) le : Wednesday, January 28, 2015 - 11:56:17 AM

File

durand_icip2013.pdf
Files produced by the author(s)

Identifiers

Citation

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⟩

Share

Metrics

Record views

123

Files downloads

137