180 search results - page 14 / 36 » Learning to segment from a few well-selected training images |
IJCV
2008
13 years 8 months ago
2008
We develop hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them. Our approach couples topic models originally developed...
CVPR
2008
IEEE
14 years 10 months ago
2008
IEEE
We present a new unsupervised method to learn unified probabilistic object models (POMs) which can be applied to classification, segmentation, and recognition. We formulate this a...
NAACL
2010
13 years 6 months ago
2010
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
ECCV
2008
Springer
14 years 10 months ago
2008
Springer
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
CVPR
2007
IEEE
14 years 10 months ago
2007
IEEE
We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models dire...