Particular Object Retrieval With Integral Max-Pooling of CNN Activations

Abstract : Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperform-ing pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN. We build compact feature vectors that encode several image regions without the need to feed multiple inputs to the network. Furthermore, we extend integral images to handle max-pooling on convolutional layer activations, allowing us to efficiently localize matching objects. The resulting bounding box is finally used for image re-ranking. As a result, this paper significantly improves existing CNN-based recognition pipeline: We report for the first time results competing with traditional methods on the challenging Oxford5k and Paris6k datasets.
Type de document :
Communication dans un congrès
ICL 2016 - RInternational Conference on Learning Representations, May 2016, San Juan, Puerto Rico. pp.1-12, International Conference on Learning Representations
Liste complète des métadonnées

https://hal.inria.fr/hal-01842218
Contributeur : Teddy Furon <>
Soumis le : mercredi 18 juillet 2018 - 09:26:23
Dernière modification le : jeudi 15 novembre 2018 - 11:59:01
Document(s) archivé(s) le : vendredi 19 octobre 2018 - 16:20:56

Fichier

1511.05879.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01842218, version 1

Citation

Giorgos Tolias, Ronan Sicre, Hervé Jégou. Particular Object Retrieval With Integral Max-Pooling of CNN Activations. ICL 2016 - RInternational Conference on Learning Representations, May 2016, San Juan, Puerto Rico. pp.1-12, International Conference on Learning Representations. 〈hal-01842218〉

Partager

Métriques

Consultations de la notice

147

Téléchargements de fichiers

50