Publicación:
On Semantic Solutions for Efficient Approximate Similarity Search on Large-Scale Datasets
On Semantic Solutions for Efficient Approximate Similarity Search on Large-Scale Datasets
No hay miniatura disponible
Fecha
2018
Autores
Ocsa, Alexander
Huillca, Jose Luis
Lopez del Alamo, Cristian
Título de la revista
Revista ISSN
Título del volumen
Editor
Springer International Publishing
Proyectos de investigación
Unidades organizativas
Número de la revista
Abstracto
Approximate similarity search algorithms based on hashing were proposed to query high-dimensional datasets due to its fast 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 heavy training process to achieve accurate query results and the critical dependency on data-parameters.
Descripción
Palabras clave
Multidimensional index,
Approximate similarity search,
Fractal theory,
Deep learning