SUN database: Large-scale scene recognition from abbey to zoo
Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object categorization contain hundre...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2011
|
| Online Access: | http://hdl.handle.net/1721.1/60690 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1811069321944760320 |
|---|---|
| author | Xiao, Jianxiong Hays, James Ehinger, Krista A. Oliva, Aude Torralba, Antonio |
| author2 | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
| author_facet | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Xiao, Jianxiong Hays, James Ehinger, Krista A. Oliva, Aude Torralba, Antonio |
| author_sort | Xiao, Jianxiong |
| collection | MIT |
| description | Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object categorization contain hundreds of different classes of objects, the largest available dataset of scene categories contains only 15 classes. In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. We use 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of performance. We measure human scene classification performance on the SUN database and compare this with computational methods. Additionally, we study a finer-grained scene representation to detect scenes embedded inside of larger scenes. |
| first_indexed | 2024-09-23T08:09:15Z |
| format | Article |
| id | mit-1721.1/60690 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:09:15Z |
| publishDate | 2011 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/606902022-09-23T11:14:32Z SUN database: Large-scale scene recognition from abbey to zoo Xiao, Jianxiong Hays, James Ehinger, Krista A. Oliva, Aude Torralba, Antonio Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Oliva, Aude Xiao, Jianxiong Ehinger, Krista A. Oliva, Aude Torralba, Antonio Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object categorization contain hundreds of different classes of objects, the largest available dataset of scene categories contains only 15 classes. In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. We use 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of performance. We measure human scene classification performance on the SUN database and compare this with computational methods. Additionally, we study a finer-grained scene representation to detect scenes embedded inside of larger scenes. National Science Foundation (U.S.) (CAREER grant 0546262) National Science Foundation (U.S.) (CAREER grant 0747120) National Science Foundation (U.S.). Graduate Fellowship Program BAE Systems National Security Solutions, Inc. (subcontract 073692) 2011-01-21T15:24:23Z 2011-01-21T15:24:23Z 2010-08 2010-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-6984-0 1063-6919 INSPEC Accession Number: 11500735 http://hdl.handle.net/1721.1/60690 Jianxiong Xiao et al. “SUN database: Large-scale scene recognition from abbey to zoo.” Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. 2010. 3485-3492. https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/CVPR.2010.5539970 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2010. CVPR 2010. Attribution-Noncommercial-Share Alike 3.0 Unported http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers MIT web domain |
| spellingShingle | Xiao, Jianxiong Hays, James Ehinger, Krista A. Oliva, Aude Torralba, Antonio SUN database: Large-scale scene recognition from abbey to zoo |
| title | SUN database: Large-scale scene recognition from abbey to zoo |
| title_full | SUN database: Large-scale scene recognition from abbey to zoo |
| title_fullStr | SUN database: Large-scale scene recognition from abbey to zoo |
| title_full_unstemmed | SUN database: Large-scale scene recognition from abbey to zoo |
| title_short | SUN database: Large-scale scene recognition from abbey to zoo |
| title_sort | sun database large scale scene recognition from abbey to zoo |
| url | http://hdl.handle.net/1721.1/60690 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT xiaojianxiong sundatabaselargescalescenerecognitionfromabbeytozoo AT haysjames sundatabaselargescalescenerecognitionfromabbeytozoo AT ehingerkristaa sundatabaselargescalescenerecognitionfromabbeytozoo AT olivaaude sundatabaselargescalescenerecognitionfromabbeytozoo AT torralbaantonio sundatabaselargescalescenerecognitionfromabbeytozoo |