On Semantic Solutions for Efficient Approximate Similarity Search on Large-Scale Datasets

• Autores: Ocsa, Alexander, Huillca, Jose Luis, Lopez del Alamo, Cristian
• Formato: capítulo de libro
• Fecha de Publicación: 2018
• Institución: Consejo Nacional de Ciencia Tecnología e Innovación
• Repositorio: CONCYTEC-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.concytec.gob.pe:20.500.12390/1310
• Enlace del recurso: https://hdl.handle.net/20.500.12390/1310; https://doi.org/10.1007/978-3-319-75193-1_54
• Nivel de acceso: acceso abierto
• Materia: Multidimensional index; Approximate similarity search; Fractal theory; Deep learning; https://purl.org/pe-repo/ocde/ford#5.08.02

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.