Visualizing object detection features
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/82370 |
| _version_ | 1811084254150393856 |
|---|---|
| author | Vondrick, Carl (Carl Martin) |
| author2 | Antonio Torralba. |
| author_facet | Antonio Torralba. Vondrick, Carl (Carl Martin) |
| author_sort | Vondrick, Carl (Carl Martin) |
| collection | MIT |
| description | Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013. |
| first_indexed | 2024-09-23T12:47:42Z |
| format | Thesis |
| id | mit-1721.1/82370 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T12:47:42Z |
| publishDate | 2013 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/823702019-04-10T12:09:57Z Visualizing object detection features Vondrick, Carl (Carl Martin) 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, 2013. Cataloged from PDF version of thesis. Includes bibliographical references (p. 59-61). We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on 'HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector's failures. For example, when we visualize high scoring false alarms, we discovered that, although they are clearly wrong in image space, they do look deceptively similar to true positives in feature space. This result suggests that many of these false alarms are caused by our choice of feature space, and indicates that creating a better learning algorithm or building bigger datasets is unlikely to correct these errors. By visualizing feature spaces, we can gain a more intuitive understanding of our detection systems. by Carl Vondrick. S.M. 2013-11-18T19:14:47Z 2013-11-18T19:14:47Z 2013 2013 Thesis http://hdl.handle.net/1721.1/82370 862074378 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 61 p. application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Vondrick, Carl (Carl Martin) Visualizing object detection features |
| title | Visualizing object detection features |
| title_full | Visualizing object detection features |
| title_fullStr | Visualizing object detection features |
| title_full_unstemmed | Visualizing object detection features |
| title_short | Visualizing object detection features |
| title_sort | visualizing object detection features |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/82370 |
| work_keys_str_mv | AT vondrickcarlcarlmartin visualizingobjectdetectionfeatures |