A unified model for accelerating unsupervised iterative re-ranking algorithms

Autor(es)

Pisani, Flavia ^{[1, 2]} ; Pascotti Valem, Lucas ^[3] ; Guimaraes Pedronette, Daniel Carlos ^[3] ; da S. Torres, Ricardo ^[4] ; Borin, Edson ^[2] ; Breternitz, Mauricio ^[5]

Afiliação do(s) autor(es)

^[1] Pontifical Catholic Univ Rio de Janeiro, Dept Informat, Rio De Janeiro, RJ - Brazil

^[2] Univ Estadual Campinas, Inst Comp, Av Albert Einstein 1251, Cidade Univ, Campinas, SP - Brazil

^[3] Sao Paulo State Univ, Dept Stat Appl Math & Comp, Rio Claro, SP - Brazil

^[4] NTNU Norwegian Univ Sci & Technol, Dept ICT & Nat Sci, Alesund - Norway

^[5] ISCTE IUL Lisbon Univ Inst, ISTAR IUL, Lisbon - Portugal

• Tipo de documento: Artigo Científico
• Fonte: CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE; v. 32, n. 14 MAR 2020.
• Citações Web of Science: 0

Resumo

Despite the continuous advances in image retrieval technologies, performing effective and efficient content-based searches remains a challenging task. Unsupervised iterative re-ranking algorithms have emerged as a promising solution and have been widely used to improve the effectiveness of multimedia retrieval systems. Although substantially more efficient than related approaches based on diffusion processes, these re-ranking algorithms can still be computationally costly, demanding the specification and implementation of efficient big multimedia analysis approaches. Such demand associated with the significant potential for parallelization and highly effective results achieved by recently proposed re-ranking algorithms creates the need for exploiting efficiency vs effectiveness trade-offs. In this article, we introduce a class of unsupervised iterative re-ranking algorithms and present a model that can be used to guide their implementation and optimization for parallel architectures. We also analyze the impact of the parallelization on the performance of four algorithms that belong to the proposed class: Contextual Spaces, RL-Sim, Contextual Re-ranking, and Cartesian Product of Ranking References. The experiments show speedups that reach up to 6.0x, 16.1x, 3.3x, and 7.1x for each algorithm, respectively. These results demonstrate that the proposed parallel programming model can be successfully applied to various algorithms and used to improve the performance of multimedia retrieval systems. (AU)

• Processo FAPESP: 14/50715-9 - Characterizing and predicting biomass production in sugarcane and eucalyptus plantations in Brazil
• Beneficiário: Rubens Augusto Camargo Lamparelli
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE
• Processo FAPESP: 13/50169-1 - Towards an understanding of tipping points within tropical South American biomes
• Beneficiário: Ricardo da Silva Torres
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE
• Processo FAPESP: 14/12236-1 - AnImaLS: Anotação de Imagem em Larga Escala: o que máquinas e especialistas podem aprender interagindo?
• Beneficiário: Alexandre Xavier Falcão
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 13/08645-0 - Reclassificação e agregação de listas para tarefas de recuperação de imagens
• Beneficiário: Daniel Carlos Guimarães Pedronette
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores
• Processo FAPESP: 13/50155-0 - Combining new technologies to monitor phenology from leaves to ecosystems
• Beneficiário: Leonor Patricia Cerdeira Morellato
• Modalidade de apoio: Auxílio à Pesquisa - Programa de Pesquisa sobre Mudanças Climáticas Globais - PITE
• Processo FAPESP: 15/24494-8 - Comunicação e processamento de big data em nuvens e névoas computacionais
• Beneficiário: Nelson Luis Saldanha da Fonseca
• Modalidade de apoio: Auxílio à Pesquisa - Temático