2026-09-19T01:18:42Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1195312026-06-06T00:49:31Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Lei Hamilton abd Antonio Torralba. Le, Tiffany Anh Mai Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2018-12-11T20:39:00Z 2018-12-11T20:39:00Z 2017 2017 http://hdl.handle.net/1721.1/119531 1066740404 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 59-60). Convolutional neural networks (CNNs), particularly those designed for object segmentation and pose estimation, are now applied to robotics applications involving mobile manipulation. For these robotic applications to be successful, robust and accurate performance from the CNNs is critical. Therefore, in order to develop an understanding of CNN performance, several CNN architectures are benchmarked on a set of metrics for object segmentation and pose estimation. This thesis presents these benchmarking results, which show that metric performance is dependent on the complexity of network architectures. The reasons behind poor pose estimation and object segmentation, which include object symmetry and resolution loss due to downsampling followed by upsampling in the networks, respectively, are also identified in this thesis. These findings can be used to guide and improve the development of CNNs for object segmentation and pose estimation in the future. by Tiffany Anh Mai Le. M.Eng. 60 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Benchmarking convolutional neural networks for object segmentation and pose estimation Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="4da77154-db31-4149-944c-f7198895294a"> <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>Benchmarking convolutional neural networks for object segmentation and pose estimation</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2017</PublicationDate> <Authors> <Author> <DisplayName>Le, Tiffany Anh Mai</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>Convolutional neural networks (CNNs), particularly those designed for object segmentation and pose estimation, are now applied to robotics applications involving mobile manipulation. For these robotic applications to be successful, robust and accurate performance from the CNNs is critical. Therefore, in order to develop an understanding of CNN performance, several CNN architectures are benchmarked on a set of metrics for object segmentation and pose estimation. This thesis presents these benchmarking results, which show that metric performance is dependent on the complexity of network architectures. The reasons behind poor pose estimation and object segmentation, which include object symmetry and resolution loss due to downsampling followed by upsampling in the networks, respectively, are also identified in this thesis. These findings can be used to guide and improve the development of CNNs for object segmentation and pose estimation in the future.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>