64 search results - page 7 / 13 » Weakly Supervised Learning on Pre-image Problem in Kernel Me... |
147
Voted
PAMI
2011
14 years 9 months ago
2011
—In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting ...
111
Voted
ICML
2006
IEEE
16 years 3 months ago
2006
IEEE
We address the problem of learning a kernel for a given supervised learning task. Our approach consists in searching within the convex hull of a prescribed set of basic kernels fo...
135
Voted
ICPR
2010
IEEE
15 years 9 months ago
2010
IEEE
This paper introduces a semi-supervised distance metric learning algorithm which uses pair-wise equivalence (similarity and dissimilarity) constraints to improve the original dist...
162
Voted
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
165
click to vote
TNN
2010
14 years 9 months ago
2010
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...