1837 search results - page 271 / 368 » Learning From Ambiguous Examples |
177
click to vote
CVPR
2010
IEEE
15 years 2 months ago
2010
IEEE
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...
161
click to vote
ML
2010
ACM
14 years 11 months ago
2010
ACM
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
178
click to vote
JMLR
2012
13 years 7 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...
220
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Metric learning is a fundamental problem in computer vision. Different features and algorithms may tackle a problem from different angles, and thus often provide complementary inf...
140
click to vote
IJCNN
2008
IEEE
15 years 11 months ago
2008
IEEE
—Since machine learning has become a tool to make more efficient design of sophisticated systems, we present in this paper a novel methodology to create powerful neural network ...