Efficient Rank-Based Diffusion Process with Assured Convergence

Autor(es)

Guimaraes Pedronette, Daniel Carlos ^[1] ; Pascotti Valem, Lucas ^[1] ; Latecki, Longin Jan ^[2]

Afiliação do(s) autor(es)

^[1] Sao Paulo State Univ UNESP, Dept Stat Appl Math & Comp DEMAC, BR-13506900 Rio Claro - Brazil

^[2] Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 - USA

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF IMAGING; v. 7, n. 3 MAR 2021.
• Citações Web of Science: 0

Resumo

Visual features and representation learning strategies experienced huge advances in the previous decade, mainly supported by deep learning approaches. However, retrieval tasks are still performed mainly based on traditional pairwise dissimilarity measures, while the learned representations lie on high dimensional manifolds. With the aim of going beyond pairwise analysis, post-processing methods have been proposed to replace pairwise measures by globally defined measures, capable of analyzing collections in terms of the underlying data manifold. The most representative approaches are diffusion and ranked-based methods. While the diffusion approaches can be computationally expensive, the rank-based methods lack theoretical background. In this paper, we propose an efficient Rank-based Diffusion Process which combines both approaches and avoids the drawbacks of each one. The obtained method is capable of efficiently approximating a diffusion process by exploiting rank-based information, while assuring its convergence. The algorithm exhibits very low asymptotic complexity and can be computed regionally, being suitable to outside of dataset queries. An experimental evaluation conducted for image retrieval and person re-ID tasks on diverse datasets demonstrates the effectiveness of the proposed approach with results comparable to the state-of-the-art. (AU)

• Processo FAPESP: 20/11366-0 - Suporte para ambiente computacional e execução de experimentos: aprendizado fracamente supervisionado e fusão de métodos de classificação
• Beneficiário: Lucas Pascotti Valem
• Modalidade de apoio: Bolsas no Brasil - Programa Capacitação - Treinamento Técnico
• Processo FAPESP: 18/15597-6 - Aplicação e investigação de métodos de aprendizado não-supervisionado em tarefas de recuperação e classificação
• Beneficiário: Daniel Carlos Guimarães Pedronette
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores - Fase 2
• Processo FAPESP: 17/25908-6 - Aprendizado fracamente supervisionado para análise de vídeos no domínio comprimido em tarefas de recuperação e classificação para alertas visuais
• Beneficiário: João Paulo Papa
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE