Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

Abstract : In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth. Three new protocols of varying difficulty are introduced. The protocols allow fair comparison between different methods, including those using a dataset preprocessing stage. For each dataset, 15 new challenging queries are introduced. Finally, a new set of 1M hard, semi-automatically cleaned distractors is selected. An extensive comparison of the state-of-the-art methods is performed on the new benchmark. Different types of methods are evaluated, ranging from local-feature-based to modern CNN based methods. The best results are achieved by taking the best of the two worlds. Most importantly, image retrieval appears far from being solved.
Type de document :
Communication dans un congrès
IEEE Computer Vision and Pattern Recognition Conference, Jun 2018, Salt Lake City, United States
Liste complète des métadonnées

https://hal.inria.fr/hal-01843075
Contributeur : Yannis Avrithis <>
Soumis le : mercredi 18 juillet 2018 - 14:41:56
Dernière modification le : vendredi 20 juillet 2018 - 01:16:57

Fichier

C107.cvpr18.oxford.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01843075, version 1
  • ARXIV : 1803.11285

Citation

Filip Radenović, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum. Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking. IEEE Computer Vision and Pattern Recognition Conference, Jun 2018, Salt Lake City, United States. 〈hal-01843075〉

Partager

Métriques

Consultations de la notice

108

Téléchargements de fichiers

19