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 centroids from the patterns in the training data sets is calculated with supervised k-means clustering. The centroids are used to generate the dissimilarity space via the Siamese networks. The vector space descriptors are extracted by projecting patterns onto the similarity spaces, and SVMs classify an image by its dissimilarity vector. The versatility of the proposed approach in image classification is demonstrated by evaluating the system on different types of images across two domains: two medical data sets and two animal audio data sets with vocalizations represented as images (spectrograms). Results show that the proposed system's performance competes competitively against the best-performing methods in the literature, obtaining state-of-the-art performance on one of the medical data sets, and does so without ad-hoc optimization of the clustering methods on the tested data sets.

Nanni L., Minchio G., Brahnam S., Maguolo G., Lumini A. (2021). Experiments of image classification using dissimilarity spaces built with siamese networks. SENSORS, 21(5), 1-18 [10.3390/s21051573].

Experiments of image classification using dissimilarity spaces built with siamese networks

Lumini A.
2021

Abstract

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 centroids from the patterns in the training data sets is calculated with supervised k-means clustering. The centroids are used to generate the dissimilarity space via the Siamese networks. The vector space descriptors are extracted by projecting patterns onto the similarity spaces, and SVMs classify an image by its dissimilarity vector. The versatility of the proposed approach in image classification is demonstrated by evaluating the system on different types of images across two domains: two medical data sets and two animal audio data sets with vocalizations represented as images (spectrograms). Results show that the proposed system's performance competes competitively against the best-performing methods in the literature, obtaining state-of-the-art performance on one of the medical data sets, and does so without ad-hoc optimization of the clustering methods on the tested data sets.
2021
Nanni L., Minchio G., Brahnam S., Maguolo G., Lumini A. (2021). Experiments of image classification using dissimilarity spaces built with siamese networks. SENSORS, 21(5), 1-18 [10.3390/s21051573].
Nanni L.; Minchio G.; Brahnam S.; Maguolo G.; Lumini A.
File in questo prodotto:
File Dimensione Formato  
sensors-21-01573-v2 (2).pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 769.72 kB
Formato Adobe PDF
769.72 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/849871
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 7
social impact