Griffin, Gregory and Holub, Alex and Perona, Pietro (2007) Caltech-256 Object Category Dataset. California Institute of Technology . (Unpublished) http://resolver.caltech.edu/CaltechAUTHORS:CNS-TR-2007-001
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:CNS-TR-2007-001
We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101  was collected by choosing a set of object categories, downloading examples from Google Images and then manually screening out all images that did not fit the category. Caltech-256 is collected in a similar manner with several improvements: a) the number of categories is more than doubled, b) the minimum number of images in any category is increased from 31 to 80, c) artifacts due to image rotation are avoided and d) a new and larger clutter category is introduced for testing background rejection. We suggest several testing paradigms to measure classification performance, then benchmark the dataset using two simple metrics as well as a state-of-the-art spatial pyramid matching  algorithm. Finally we use the clutter category to train an interest detector which rejects uninformative background regions.
|Item Type:||Report or Paper (Technical Report)|
|Subject Keywords:||vision detection dataset collection pyramid matching kernel clutter testing|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Gregory Griffin|
|Deposited On:||19 Apr 2007|
|Last Modified:||26 Dec 2012 09:34|
Repository Staff Only: item control page