Datasets
Skip Navigation LinksHome > Datasets
  [Login]


  Caltech101-PMK 
Added: Tuesday, May 27, 2008 by Eric Garcia - University of Washington
        Tags: Dense, Large, PSD, Symmetric, Vision
   Description The Caltech-101 data set (Fei-Fei et al., 2004) is an object recognition benchmark dataset consisting of 8677 images from 101 object categories. Similarities between images were computed using the pyramid match kernel (Grauman and Darrell, 2007) on SIFT features (Lowe, 1999). The similarity is positive definite.
   Details 101 Classes, 8677 Instances, Dense, Symmetric
   Download ZIP Archive [195759 kb]
   Comments No Comments.



This site created and maintained with support from the United States Office of Naval Research