<rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:dct="http://purl.org/dc/terms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
  <rdf:Description rdf:about="https://doi.org/20.500.14243/517581">
    <dct:isReferencedBy>OPENAIRE</dct:isReferencedBy>
    <dct:isReferencedBy>OpenAire</dct:isReferencedBy>
    <dct:isReferencedBy>Datacite</dct:isReferencedBy>
    <dct:isReferencedBy>IRIS Cnr</dct:isReferencedBy>
    <dct:references>https://iris.cnr.it/bitstream/20.500.14243/517581/1/TestingSARbasedShipClassifierwithDifferentLossFunctions.pdf</dct:references>
    <dct:references>https://doi.org/20.500.14243/517581</dct:references>
    <dcat:downloadURL rdf:resource="https://iris.cnr.it/bitstream/20.500.14243/517581/1/TestingSARbasedShipClassifierwithDifferentLossFunctions.pdf"/>
    <dct:license>Open Access</dct:license>
    <dct:available>2024-12-15</dct:available>
    <dc:description>This study investigated the influence of six different loss functions on Synthetic Aperture Radar (SAR) ship classification accuracy across two datasets. Kullback-Leibler Divergence Loss emerged with the highest average accuracy (69.5%), followed by L1 Loss (69.12%) and Focal Loss(68.4%). Interestingly, L1 and Focal Loss exhibited contrasting performance across datasets, suggesting potential data-specific suitability for certain functions. These findings highlight the importance of considering data characteristics and task requirements when selecting loss functions to optimize SAR ship classification performance.</dc:description>
    <dc:subject>Loss Functions, Deep Learning, Ship Classification, SAR</dc:subject>
    <dc:creator rdf:resource="https://orcid.org/0009-0001-4589-4103"/>
    <dc:creator>Awais Ch. M., Reggiannini M., Moroni D., </dc:creator>
    <dc:date>2024-01-01</dc:date>
    <dct:abstract>This study investigated the influence of six different loss functions on Synthetic Aperture Radar (SAR) ship classification accuracy across two datasets. Kullback-Leibler Divergence Loss emerged with the highest average accuracy (69.5%), followed by L1 Loss (69.12%) and Focal Loss(68.4%). Interestingly, L1 and Focal Loss exhibited contrasting performance across datasets, suggesting potential data-specific suitability for certain functions. These findings highlight the importance of considering data characteristics and task requirements when selecting loss functions to optimize SAR ship classification performance.</dct:abstract>
    <dc:title>Testing a SAR-based ship classifier with different loss functions</dc:title>
    <dc:identifier>20.500.14243/517581</dc:identifier>
    <dc:type>publication</dc:type>
    <dct:relation>101025891</dct:relation>
  </rdf:Description>
</rdf:RDF>