Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Contextual Spaces Re-Ranking: accelerating the Re-sort Ranked Lists step on heterogeneous systems

Full text
Author(s):
Pisani, Flavia [1] ; Pedronette, Daniel C. G. [2] ; Torres, Ricardo da S. [1] ; Borin, Edson [1]
Total Authors: 4
Affiliation:
[1] Univ Campinas UNICAMP, IC, Campinas, SP - Brazil
[2] Sao Paulo State Univ UNESP, Inst Geosci & Exact Sci IGCE, Rio Claro, SP - Brazil
Total Affiliations: 2
Document type: Journal article
Source: CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE; v. 29, n. 22, SI NOV 25 2017.
Web of Science Citations: 1
Abstract

Re-ranking algorithms have been proposed to improve the effectiveness of content-based image retrieval systems by exploiting contextual information encoded in distance measures and ranked lists. In this paper, we show how we improved the efficiency of one of these algorithms, called Contextual Spaces Re-Ranking (CSRR). One of our approaches consists in parallelizing the algorithm with OpenCL to use the central and graphics processing units of an accelerated processing unit. The other is to modify the algorithm to a version that, when compared with the original CSRR, not only reduces the total running time of our implementations by a median of 1.6x but also increases the accuracy score in most of our test cases. Combining both parallelization and algorithm modification results in a median speedup of 5.4x from the original serial CSRR to the parallelized modified version. Different implementations for CSRR's Re-sort Ranked Lists step were explored as well, providing insights into graphics processing unit sorting, the performance impact of image descriptors, and the trade-offs between effectiveness and efficiency. Copyright (c) 2016 John Wiley \& Sons, Ltd. (AU)

FAPESP's process: 13/08645-0 - Re-Ranking and rank aggregation approaches for image retrieval tasks
Grantee:Daniel Carlos Guimarães Pedronette
Support type: Research Grants - Young Investigators Grants