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.
|Title of host publication||2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||6|
|State||Published - 7 Feb 2018|
|Event||2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Arequipa, Peru|
Duration: 8 Nov 2017 → 10 Nov 2017
|Name||2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings|
|Conference||2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017|
|Period||8/11/17 → 10/11/17|
Bibliographical noteFunding Information:
This project has been partially funded by CIENCIA-ACTIVA (Perú) through the Doctoral Scholarship at UNSA University, and FONDECYT (Perú) Project 148-2015.
© 2017 IEEE.