Visual tasks beyond categorization for training convolutional neural networks
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2016
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/106095 |
| _version_ | 1826215949595836416 |
|---|---|
| author | Lee, Hyo-Dong |
| author2 | James J. DiCarlo. |
| author_facet | James J. DiCarlo. Lee, Hyo-Dong |
| author_sort | Lee, Hyo-Dong |
| collection | MIT |
| description | Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016. |
| first_indexed | 2024-09-23T16:40:03Z |
| format | Thesis |
| id | mit-1721.1/106095 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T16:40:03Z |
| publishDate | 2016 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1060952019-04-10T18:04:47Z Visual tasks beyond categorization for training convolutional neural networks Lee, Hyo-Dong James J. DiCarlo. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. 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. 2016-12-22T16:28:48Z 2016-12-22T16:28:48Z 2016 2016 Thesis http://hdl.handle.net/1721.1/106095 965383395 eng 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 23 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Lee, Hyo-Dong Visual tasks beyond categorization for training convolutional neural networks |
| title | Visual tasks beyond categorization for training convolutional neural networks |
| title_full | Visual tasks beyond categorization for training convolutional neural networks |
| title_fullStr | Visual tasks beyond categorization for training convolutional neural networks |
| title_full_unstemmed | Visual tasks beyond categorization for training convolutional neural networks |
| title_short | Visual tasks beyond categorization for training convolutional neural networks |
| title_sort | visual tasks beyond categorization for training convolutional neural networks |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/106095 |
| work_keys_str_mv | AT leehyodong visualtasksbeyondcategorizationfortrainingconvolutionalneuralnetworks |