<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T10:04:25Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/70292" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/70292</identifier><datestamp>2026-05-15T19:42:51Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Eshed, Noam</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair">Hariharan, Bharath</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember">Field, David</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2020-08-10T20:07:36Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2020-08-10T20:07:36Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2020-05</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 10906</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 27994027</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/70292</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/7273-6v18</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">13254539</dim:field>
   <dim:field mdschema="dc" element="description">97 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">While many computer vision researchers race to architect improved convolutional neural networks (CNNs) and increase task accuracy, relatively little work has been done to understand and quantify the types of errors networks make. Regarding classification networks, certain incorrect responses may be better than others. In an animal classification task, for instance, the network categorizes an input image as one out of a set of trained labels. When such a network gets the label incorrect, there are many wrong labels it can choose. There are, however, varying degrees of incorrectness; a network which classifies a German shepherd as a poodle is a better network than one which classifies the German shepherd as a blue whale. In this work, I explore the responses of CNNs to sets of images in both known classes and novel classes (those which the network was not trained on). I analyze the predicted labels for these sets of images, as well as the predicted label distribution over many images in a given class. This paper  also includes a discussion of the hierarchy of predicted labels and true labels, and what a network’s response in terms of higher-level categories reveals about its ability to generalize. Finally, I will discuss how humans and networks each measure the similarity between images, and show novelty's effect on networks' agreement with people.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights">Attribution 4.0 International</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">https://creativecommons.org/licenses/by/4.0/</dim:field>
   <dim:field mdschema="dc" element="subject">alexnet</dim:field>
   <dim:field mdschema="dc" element="subject">CNN</dim:field>
   <dim:field mdschema="dc" element="subject">computer vision</dim:field>
   <dim:field mdschema="dc" element="subject">convolutional neural network</dim:field>
   <dim:field mdschema="dc" element="subject">imagenet</dim:field>
   <dim:field mdschema="dc" element="subject">novelty</dim:field>
   <dim:field mdschema="dc" element="title">Novelty Detection and Analysis in Convolutional Neural Networks</dim:field>
   <dim:field mdschema="dc" element="type">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="localuri">https://catalog.library.cornell.edu/catalog/13254539</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Computer Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Master of Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">M.S., Computer Science</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://cornell-ecommons.eks.prod.4science.cloud/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Eshed, Noam</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b63fe671-02c5-4c83-9ca3-ecb36196f67d">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en&lt;/Language>
   	&lt;Title>Novelty Detection and Analysis in Convolutional Neural Networks&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2020-05&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/7273-6v18&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Eshed, Noam&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;License>https://creativecommons.org/licenses/by/4.0/&lt;/License>
    &lt;Keyword>alexnet&lt;/Keyword>
    &lt;Keyword>CNN&lt;/Keyword>
    &lt;Keyword>computer vision&lt;/Keyword>
    &lt;Keyword>convolutional neural network&lt;/Keyword>
    &lt;Keyword>imagenet&lt;/Keyword>
    &lt;Keyword>novelty&lt;/Keyword>
   	&lt;Abstract>While many computer vision researchers race to architect improved convolutional neural networks (CNNs) and increase task accuracy, relatively little work has been done to understand and quantify the types of errors networks make. Regarding classification networks, certain incorrect responses may be better than others. In an animal classification task, for instance, the network categorizes an input image as one out of a set of trained labels. When such a network gets the label incorrect, there are many wrong labels it can choose. There are, however, varying degrees of incorrectness; a network which classifies a German shepherd as a poodle is a better network than one which classifies the German shepherd as a blue whale. In this work, I explore the responses of CNNs to sets of images in both known classes and novel classes (those which the network was not trained on). I analyze the predicted labels for these sets of images, as well as the predicted label distribution over many images in a given class. This paper  also includes a discussion of the hierarchy of predicted labels and true labels, and what a network’s response in terms of higher-level categories reveals about its ability to generalize. Finally, I will discuss how humans and networks each measure the similarity between images, and show novelty&amp;apos;s effect on networks&amp;apos; agreement with people.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>