Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks

Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks

In this paper, we examine two strategies for boosting the performance of ensembles of Siamese networks (SNNs) for image classification using two loss functions (Triplet and Binary Cross Entropy) and two methods for building the dissimilarity spaces (FULLY and DEEPER). With FULLY, the distance betwee...

Full description

Bibliographic Details
Main Authors: Loris Nanni, Giovanni Minchio, Sheryl Brahnam, Davide Sarraggiotto, Alessandra Lumini
Format: Article
Language:English
Published: MDPI AG 2021-08-01
Series:Sensors
Subjects:
Siamese networks
ensemble of classifiers
loss function
discrete cosine transform
Online Access:https://www.mdpi.com/1424-8220/21/17/5809

Internet

https://www.mdpi.com/1424-8220/21/17/5809

Similar Items