Image search with selective match kernels: aggregation across single and multiple images

Abstract : This paper considers a family of metrics to compare images based on their local descriptors. It encompasses the VLAD descriptor and matching techniques such as Hamming Embedding. Making the bridge between these approaches leads us to propose a match kernel that takes the best of existing techniques by combining an aggregation procedure with a selective match kernel. The representation underpinning this kernel is approximated, providing a large scale image search both precise and scalable, as shown by our experiments on several benchmarks. We show that the same aggregation procedure, originally applied per image, can effectively operate on groups of similar features found across multiple images. This method implicitly performs feature set augmentation, while enjoying savings in memory requirements at the same time. Finally, the proposed method is shown effective for place recognition , outperforming state of the art methods on a large scale landmark recognition benchmark.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [52 references]  Display  Hide  Download

https://hal.inria.fr/hal-01131898
Contributor : Giorgos Tolias <>
Submitted on : Monday, March 16, 2015 - 12:29:56 PM
Last modification on : Thursday, November 15, 2018 - 11:58:51 AM
Document(s) archivé(s) le : Monday, April 17, 2017 - 2:53:33 PM

File

ToliasAvrithisJegou_IJCV2015_I...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01131898, version 1

Citation

G. Tolias, Yannis Avrithis, Hervé Jégou. Image search with selective match kernels: aggregation across single and multiple images. International Journal of Computer Vision, Springer Verlag, 2015, pp.00. ⟨hal-01131898⟩

Share

Metrics

Record views

431

Files downloads

1533