Transfer learning by borrowing examples for multiclass object detection
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/78467 |
| _version_ | 1811088929045086208 |
|---|---|
| author | Lim, Joseph J. (Joseph Jaewhan) |
| author2 | Antonio Torralba. |
| author_facet | Antonio Torralba. Lim, Joseph J. (Joseph Jaewhan) |
| author_sort | Lim, Joseph J. (Joseph Jaewhan) |
| collection | MIT |
| description | Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012. |
| first_indexed | 2024-09-23T14:10:10Z |
| format | Thesis |
| id | mit-1721.1/78467 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T14:10:10Z |
| publishDate | 2013 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/784672019-04-12T16:11:16Z Transfer learning by borrowing examples for multiclass object detection Lim, Joseph J. (Joseph Jaewhan) Antonio Torralba. 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, Dept. of Electrical Engineering and Computer Science, 2012. Cataloged from PDF version of thesis. Includes bibliographical references (p. 31-33). Despite the recent trend of increasingly large datasets for object detection, there still exist many classes with few training examples. To overcome this lack of training data for certain classes, we propose a novel way of augmenting the training data for each class by borrowing and transforming examples from other classes. Our model learns which training instances from other classes to borrow and how to transform the borrowed examples so that they become more similar to instances from the target class. Our experimental results demonstrate that our new object detector, with borrowed and transformed examples, improves upon the current state-of-the-art detector on the challenging SUN09 object detection dataset. by Joseph J. Lim. S.M. 2013-04-12T19:26:57Z 2013-04-12T19:26:57Z 2012 2012 Thesis http://hdl.handle.net/1721.1/78467 834089202 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 33 p. application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Lim, Joseph J. (Joseph Jaewhan) Transfer learning by borrowing examples for multiclass object detection |
| title | Transfer learning by borrowing examples for multiclass object detection |
| title_full | Transfer learning by borrowing examples for multiclass object detection |
| title_fullStr | Transfer learning by borrowing examples for multiclass object detection |
| title_full_unstemmed | Transfer learning by borrowing examples for multiclass object detection |
| title_short | Transfer learning by borrowing examples for multiclass object detection |
| title_sort | transfer learning by borrowing examples for multiclass object detection |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/78467 |
| work_keys_str_mv | AT limjosephjjosephjaewhan transferlearningbyborrowingexamplesformulticlassobjectdetection |