Loading...
Please wait, while we are loading the content...
Similar Documents
Slightly Supervised Learning of Part-Based Appearance Models (2004)
| Content Provider | CiteSeerX |
|---|---|
| Author | Perez, Patrick Xie, Lexing |
| Abstract | We extend the GMM-based approach of [17], for learning part-based appearance models of object categories, to the unsupervised case where positive examples are corrupted with clutter. To this end, we derive an original version of EM which is able to fit one GMM per class based on partially labeled data. We also allow ourselves a small fraction of un-corrupted positive examples, thus obtaining an effective, yet cheap, slightly supervised learning. Proposed technique allows as well a saliency-based ranking and selection of learnt mixture components. Experiments show that both the semi-supervised GMM fitting with side information and the component selection are effective in identifying salient patches in the appearance of a class of objects. They are thus promising tools to learn class-specific models and detectors similar to those by Weber et al.[6], but at a lower computational cost, while accommodating larger numbers of atomic parts. |
| File Format | |
| Journal | IEEE Workshop on Learning in CVPR |
| Publisher Date | 2004-01-01 |
| Access Restriction | Open |
| Subject Keyword | Salient Patch Unsupervised Case Atomic Part Gmm-based Approach Component Selection Learnt Mixture Component Saliency-based Ranking Part-based Appearance Model Un-corrupted Positive Example Object Category Class-specific Model Semi-supervised Gmm Fitting |
| Content Type | Text |
| Resource Type | Conference Proceedings |
