Published October 26, 2011
| Published
Report
Open
Caltech-UCSD Birds 200
Abstract
Caltech-UCSD Birds 200 (CUB-200) is a challenging image dataset annotated with 200 bird species. It was created to enable the study of subordinate categorization, which is not possible with other popular datasets that focus on basic level categories (such as PASCAL VOC, Caltech-101, etc). The images were downloaded from the website Flickr and filtered by workers on Amazon Mechanical Turk. Each image is annotated with a bounding box, a rough bird segmentation, and a set of attribute labels.
Attached Files
Published - WelinderEtal10_CUB-200.pdf
Files
WelinderEtal10_CUB-200.pdf
Files
(5.9 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:bed93091d41b331fc8dcbc5d4eb5d5a9
|
5.9 MB | Preview Download |
Additional details
- Eprint ID
- 27468
- Resolver ID
- CaltechAUTHORS:20111026-155425465
- Created
-
2011-10-26Created from EPrint's datestamp field
- Updated
-
2021-11-23Created from EPrint's last_modified field
- Caltech groups
- Computation & Neural Systems Technical Reports
- Series Name
- Computation & Neural Systems Technical Report
- Series Volume or Issue Number
- 2010-001