In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes com- puted using a multiple k-means assignment. The method has been applied to the problem of approximate nearest neighbor (ANN) search of local and global visual content descriptors, and it has been tested on different datasets: three large scale standard datasets of engineered features of up to one billion descriptors (BIGANN) and, supported by recent progress in convolutional neural networks (CNNs), on CIFAR-10, MNIST, INRIA Holidays, Oxford 5K and Paris 6K datasets; also the recent DEEP1B dataset, composed by one billion CNN-based features, has been used. Experimental results show that, despite its simplicity, the proposed method obtains a very high performance that makes it superior to more complex state-of-the-art methods.

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases / Ercoli, Simone; Bertini, Marco; Del Bimbo, Alberto. - In: IEEE TRANSACTIONS ON MULTIMEDIA. - ISSN 1520-9210. - ELETTRONICO. - 19:(2017), pp. 2521-2532. [10.1109/TMM.2017.2697824]

Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

ERCOLI, SIMONE;BERTINI, MARCO;DEL BIMBO, ALBERTO
2017

Abstract

In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes com- puted using a multiple k-means assignment. The method has been applied to the problem of approximate nearest neighbor (ANN) search of local and global visual content descriptors, and it has been tested on different datasets: three large scale standard datasets of engineered features of up to one billion descriptors (BIGANN) and, supported by recent progress in convolutional neural networks (CNNs), on CIFAR-10, MNIST, INRIA Holidays, Oxford 5K and Paris 6K datasets; also the recent DEEP1B dataset, composed by one billion CNN-based features, has been used. Experimental results show that, despite its simplicity, the proposed method obtains a very high performance that makes it superior to more complex state-of-the-art methods.
2017
19
2521
2532
Ercoli, Simone; Bertini, Marco; Del Bimbo, Alberto
File in questo prodotto:
File Dimensione Formato  
07911248.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 966.27 kB
Formato Adobe PDF
966.27 kB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1089824
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 40
  • ???jsp.display-item.citation.isi??? 32
social impact