Skip to Content
You are currently on the new version of our website. Access the old version .
SensorsSensors
  • Article
  • Open Access

29 August 2021

15 Pages

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

,
,
,
and
1
Department of Information Engineering (DEI), University of Padova, 35131 Padova, Italy
2
Department of Information Technology and Cybersecurity, Missouri State University, 901 S, National Street, Springfield, MO 65804, USA
3
Department of Computer Science and Engineering (DISI), University of Bologna, Via dell’Università 50, 47521 Cesena, Italy
*
Author to whom correspondence should be addressed.
This article belongs to the Special Issue 800 Years of Research at Padova University

Abstract

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 between a pattern and a prototype is calculated by comparing two images using the fully connected layer of the Siamese network. With DEEPER, each pattern is described using a deeper layer combined with dimensionality reduction. The basic design of the SNNs takes advantage of supervised k-means clustering for building the dissimilarity spaces that train a set of support vector machines, which are then combined by sum rule for a final decision. The robustness and versatility of this approach are demonstrated on several cross-domain image data sets, including a portrait data set, two bioimage and two animal vocalization data sets. Results show that the strategies employed in this work to increase the performance of dissimilarity image classification using SNN are closing the gap with standalone CNNs. Moreover, when our best system is combined with an ensemble of CNNs, the resulting performance is superior to an ensemble of CNNs, demonstrating that our new strategy is extracting additional information.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.