712 search results - page 52 / 143 » Pruning Training Sets for Learning of Object Categories |
GECCO
2006
Springer
14 years 22 days ago
2006
Springer
This paper proposes a new smart crossover operator for a Pittsburgh Learning Classifier System. This operator, unlike other recent LCS approaches of smart recombination, does not ...
MMM
2007
Springer
14 years 3 months ago
2007
Springer
This paper investigates the problem of learning the visual semantics of keyword categories for automatic image annotation. Supervised learning algorithms which learn only a single ...
PAMI
2008
13 years 9 months ago
2008
We construct an image segmentation scheme that combines top-down (TD) with bottom-up (BU) processing. In the proposed scheme, segmentation and recognition are intertwined rather th...
JMLR
2012
11 years 11 months ago
2012
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
CIARP
2007
Springer
14 years 3 months ago
2007
Springer
The main difficulty in the binary object classification field lays in dealing with a high variability of symbol appearance. Rotation, partial occlusions, elastic deformations, or...