Visual tasks beyond categorization for training convolutional neural networks
Name
965383395-MIT.pdf
Description
Full printable version
Size
1.98 MB
Format
Adobe PDF
Checksum (MD5)
cc3d6064591b8c7d213bf36592357f09
Author(s)
Lee, Hyo-Dong
Advisor(s)
James J. DiCarlo.
Date Issued
2016
Publisher
Massachusetts Institute of Technology
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.
Description
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).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
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.
Persistent DSpace Link
