Approximate nearest neighbors by deep hashing on large-scale search: Comparison of representations and retrieval performance

Alexander Ocsa, Jose Luis Huillca, Ricardo Coronado, Oscar Quispe, Carlos Arbieto, Cristian Lopez

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

Resumen

The growing volume of data and its increasing complexity require even more efficient and faster information retrieval techniques. Approximate nearest neighbor search algorithms based on hashing were proposed to query high-dimensional datasets due to its high retrieval speed and low storage cost. Recent studies promote the use of Convolutional Neural Network (CNN) with hashing techniques to improve the search accuracy. However, there are challenges to solve in order to find a practical and efficient solution to index CNN features, such as the need for a heavy training process to achieve accurate query results and the critical dependency on data-parameters. In this work we execute exhaustive experiments in order to compare recent methods that are able to produces a better representation of the data space with a less computational cost for a better accuracy by computing the best data-parameter values for optimal sub-space projection exploring the correlations among CNN feature attributes using fractal theory. We give an overview of these different techniques and present our comparative experiments for data representation and retrieval performance.

Idioma originalInglés
Título de la publicación alojada2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1-6
Número de páginas6
ISBN (versión digital)9781538637340
DOI
EstadoPublicada - 7 feb. 2018
Publicado de forma externa
Evento2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Arequipa, Perú
Duración: 8 nov. 201710 nov. 2017

Serie de la publicación

Nombre2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
Volumen2017-November

Conferencia

Conferencia2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017
País/TerritorioPerú
CiudadArequipa
Período8/11/1710/11/17

Nota bibliográfica

Publisher Copyright:
© 2017 IEEE.

Huella

Profundice en los temas de investigación de 'Approximate nearest neighbors by deep hashing on large-scale search: Comparison of representations and retrieval performance'. En conjunto forman una huella única.

Citar esto