2026-09-18T21:58:47Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1060952022-01-13T07:54:01Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
James J. DiCarlo.
Lee, Hyo-Dong
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2016-12-22T16:28:48Z
2016-12-22T16:28:48Z
2016
2016
http://hdl.handle.net/1721.1/106095
965383395
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 21-23).
Humans can perceive a variety of visual properties of objects besides their category. In this paper, we explore- whether convolutional neural networks (CNNs) can also learn object-related variables. The models are trained for object position, size and pose, respectively, from synthetic images and tested on unseen held-out objects. First, we show that some object properties come "for free" from learning others, and pose-optimized model can generalize to both categorical and non-categorical variables. Second, we demonstrate that pre-training the model with pose facilitates learning object categories from both synthetic and realistic images.
by Hyodong Lee.
S.M.
23 pages
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Visual tasks beyond categorization for training convolutional neural networks
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="ece6b696-61ce-4f8e-91a2-1786264bef14">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Visual tasks beyond categorization for training convolutional neural networks</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2016</PublicationDate>
<Authors>
<Author>
<DisplayName>Lee, Hyo-Dong</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Humans can perceive a variety of visual properties of objects besides their category. In this paper, we explore- whether convolutional neural networks (CNNs) can also learn object-related variables. The models are trained for object position, size and pose, respectively, from synthetic images and tested on unseen held-out objects. First, we show that some object properties come "for free" from learning others, and pose-optimized model can generalize to both categorical and non-categorical variables. Second, we demonstrate that pre-training the model with pose facilitates learning object categories from both synthetic and realistic images.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>