No Detail Found!

Extended relational autoencoders for feature extraction in CBIR

Author(s)
M. K. Bashir Department of Statistics & Computer Science, University of Veterinary & Animal Sciences,Lahore,Pakistan
Y. Saleem Department of Computer Science & Engineering, University of Engineering and Technology,Lahore,Pakistan
S. Naseer Department of Computer Science, University of Management and Technology,Lahore,Pakistan
Abstract
As high dimensional data is increasing day by day, importance of fast and precise features extraction is also increasing. Huge work in deep learning leads to autoencoders that are very useful methods for feature extraction as they tend to recreate the original data from same features. In deep learning, a lot depends on loss and objective function. Normally loss functions depend on input data without any relationship between input data. In this study, an extended relational model for autoencoders has been proposed that maps original data on the basis of data with combination to relation between data. This relation is based on ratio between data variance and magnitude. Convolutional autoencoder has been evaluated with proposed relational model in this study. Benchmark datasets of Mnist and Cifar10 have been used for experimental results. Comparison of proposed model has been made with different available loss functions and experimentally it has been proved that proposed relational model achieve lower construction loss with better accuracy and visual results.
Publication Details
Page(s) 26-36
DOI DOI not available
Published Journal: Technical Journal, Volume: 25, Issue: 4, Year: 2020

Request the full text from PASTIC

Keywords
Nanoparticles (NPs), Localized surface plasmon resonance (LSPR), Surface plasmon resonance (SPR), Nanocomposites (NCs), Plasmonic superabsorber (PSA), Metamaterials, - Surface plasmons
0

Citations

0

Downloads

53

Views