January 5, 2024 Other Open Access

Alessandro Bombini; Fernando García-Avello Bofías; Caterina Bracci; Michele Ginolfi; Chiara Ruberto

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.15161/oar.it/143543</identifier>
  <creators>
    <creator>
      <creatorName>Alessandro Bombini</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-7225-3355</nameIdentifier>
      <affiliation>INFN, Firenze &amp; ICSC</affiliation>
    </creator>
    <creator>
      <creatorName>Fernando García-Avello Bofías</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-6640-8736</nameIdentifier>
      <affiliation>INFN, Firenze</affiliation>
    </creator>
    <creator>
      <creatorName>Caterina Bracci</creatorName>
      <affiliation>Università di Firenze &amp; INAF, Firenze</affiliation>
    </creator>
    <creator>
      <creatorName>Michele Ginolfi</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-9122-1700</nameIdentifier>
      <affiliation>Università di Firenze &amp; INAF, Firenze</affiliation>
    </creator>
    <creator>
      <creatorName>Chiara Ruberto</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-0321-7160</nameIdentifier>
      <affiliation>Università di Firenze &amp; INFN, Firenze</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Trained Models for ICSC Flagship 2.6.1. "Extended Computer Vision at high rate" paper #1 "Datacube segmentation via Deep Spectral Clustering"</title>
  </titles>
  <publisher>INFN Open Access Repository</publisher>
  <publicationYear>2024</publicationYear>
  <subjects>
    <subject>artificial intelligence</subject>
    <subject>neural networks</subject>
    <subject>Variational Autoencoder</subject>
    <subject>Deep Clustering</subject>
    <subject>Trained Models</subject>
    <subject>Flagship 2.6.1</subject>
    <subject>ICSC Spoke 2</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2024-01-05</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Other"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://www.openaccessrepository.it/record/143543</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/ICSC-Spoke2-repo/FastExtendedVision-DeepCluster</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsSupplementedBy">10.15161/oar.it/143545</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.15161/oar.it/143542</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://www.openaccessrepository.it/communities/infn</relatedIdentifier>
  </relatedIdentifiers>
  <version>20240105</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Trained models for the paper &amp;quot;Datacube segmentation via Deep Spectral Clustering&amp;quot;.&lt;br&gt;
It is a preliminary paper for the ICSC Spoke 2 WP6 flagship 2.6.1 &amp;quot;Fast Extended Computer Vision&amp;quot;.&lt;/p&gt;

&lt;p&gt;Code repository at: https://github.com/ICSC-Spoke2-repo/FastExtendedVision-DeepCluster&lt;/p&gt;

&lt;p&gt;Abstract:&lt;/p&gt;

&lt;blockquote&gt;
&lt;p&gt;Extended Vision techniques are a ubiquitous in physics. However, the&amp;nbsp; data cubes steaming from such analysis often pose a challenge in their interpretation, due to the intrinsic difficulty in discerning the relevant information from the spectra composing the data cube.&lt;br&gt;
Furthermore, the huge dimensionality of data cube spectra poses a complex task in its statistical interpretation; nevertheless, this complexity contains a massive amount of statistical information that can be exploited in an unsupervised manner to outiline some essential properties of the case study at hand, e.g.~it is possible to obtain an image segmentation via (deep) clustering of data-cube&amp;#39;s spectra, performed in a suitably defined low-dimensional embedding space.&lt;br&gt;
To tackle this topic, we explore the possibility of applying unsupervised clustering methods in encoded space, i.e.~perform deep clustering on the spectral properties of datacube pixels. A statistical dimensional reduction is performed by an ad hoc trained AutoEncoder, in charge of mapping spectra into lower dimensional metric spaces, while the clustering process is performed by an iterative K-Means clustering algorithm.&lt;br&gt;
We apply this technique on two different use cases, of different physical origin: a set of MA-XRF data on pictorial artworks, and a synthetic dataset of simualted astrophysical observations.&lt;/p&gt;
&lt;/blockquote&gt;</description>
    <description descriptionType="Other">This work is (partially) supported by ICSC – Centro Nazionale di Ricerca in High Performance Computing, Big Data and Quantum Computing, funded by European Union – NextGenerationEU, by the European Commission within the Framework Programme Horizon 2020 with the project "4CH - Competence Centre for the Conservation of Cultural Heritage"  (GA n.101004468 – 4CH) and by the project AIRES–CH - Artificial Intelligence for digital REStoration of Cultural Heritage jointly funded by the Tuscany Region (Progetto Giovani Sì) and INFN.</description>
  </descriptions>
</resource>