Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Traditionally, classifiers are trained to predict patterns within a feature space. The image classification system presented here trains classifiers to predict patterns within a vector space by combining the dissimilarity spaces generated by a large set of Siamese Neural Networks (SNNs). A set of ce...

Full description

Bibliographic Details

Published in:	Sensors
Main Authors:	Loris Nanni, Giovanni Minchio, Sheryl Brahnam, Gianluca Maguolo, Alessandra Lumini
Format:	Article
Language:	English
Published:	MDPI AG 2021-02-01
Subjects:	audio sound classification image classification clustering prototype selection siamese network dissimilarity space
Online Access:	https://www.mdpi.com/1424-8220/21/5/1573