Conference paper Open Access

INPUT COMPLEXITY AND OUT-OF-DISTRIBUTION DETECTION WITH LIKELIHOOD-BASED GENERATIVE MODELS

Serra, Joan; Álvarez, David; Gómez, Vicenç; Slizovskaia , Olga; F. Núñez, José; Luque, Jordi


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">10.5281/zenodo.5253740</identifier>
  <creators>
    <creator>
      <creatorName>Serra, Joan</creatorName>
      <givenName>Joan</givenName>
      <familyName>Serra</familyName>
      <affiliation>Dolby Laboratories,  Barcelona, Spain</affiliation>
    </creator>
    <creator>
      <creatorName>Álvarez, David</creatorName>
      <givenName>David</givenName>
      <familyName>Álvarez</familyName>
      <affiliation>Universitat Politècnica de Catalunya,  Barcelona, Spain</affiliation>
    </creator>
    <creator>
      <creatorName>Gómez, Vicenç</creatorName>
      <givenName>Vicenç</givenName>
      <familyName>Gómez</familyName>
      <affiliation>Universitat Pompeu Fabra, Barcelona, Spain</affiliation>
    </creator>
    <creator>
      <creatorName>Slizovskaia , Olga</creatorName>
      <givenName>Olga</givenName>
      <familyName>Slizovskaia</familyName>
      <affiliation>Universitat Pompeu Fabra, Barcelona, Spain</affiliation>
    </creator>
    <creator>
      <creatorName>F. Núñez, José</creatorName>
      <givenName>José</givenName>
      <familyName>F. Núñez</familyName>
      <affiliation>Universitat Pompeu Fabra, Barcelona, Spain</affiliation>
    </creator>
    <creator>
      <creatorName>Luque, Jordi</creatorName>
      <givenName>Jordi</givenName>
      <familyName>Luque</familyName>
      <affiliation>Telefónica I+D, Research, Barcelona, Spain</affiliation>
    </creator>
  </creators>
  <titles>
    <title>INPUT COMPLEXITY AND OUT-OF-DISTRIBUTION DETECTION WITH LIKELIHOOD-BASED GENERATIVE MODELS</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <dates>
    <date dateType="Issued">2020-04-30</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5253740</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.5253739</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/accordion</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Likelihood-based generative models are a promising resource to detect out-of- distribution (OOD) inputs which could compromise the&amp;nbsp;robustness or reliability of a machine learning system. However, likelihoods derived from such models have been shown to be problematic for detecting certain types of inputs that sig- nificantly differ from training data. In this paper, we pose that this problem is due to the excessive influence that input complexity has in generative models&amp;rsquo; likelihoods. We report a set of experiments supporting this hypothesis, and use an estimate of input complexity to derive an efficient and parameter-free OOD score, which can be seen as a likelihood-ratio, akin to Bayesian model compari- son. We find such score to perform comparably to, or even better than, existing OOD detection approaches under a wide range of data sets, models, model sizes, and complexity estimates.&lt;/p&gt;</description>
    <description descriptionType="Other">Accepted for ICLR2020</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/871793/">871793</awardNumber>
      <awardTitle>Adaptive edge/cloud compute and network continuum over a heterogeneous sparse edge infrastructure to support nextgen applications</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
17
12
views
downloads
All versions This version
Views 1717
Downloads 1212
Data volume 23.3 MB23.3 MB
Unique views 1414
Unique downloads 1212

Share

Cite as