We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a multi-class boosting procedure (joint boosting) that reduces both the computational and sample complexity, by finding common features that can be shared across the classes. The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required is observed to scale approximately logarithmically with the number of classes. In addition, we find that the features selected by independently trained classifiers are often specific to the class, whereas the features selected by the jointly trained classifiers are more generic features, such as lines and edges.
Sharing features: efficient boosting procedures for multiclass object detection
2004-01-01
738178 byte
Conference paper
Electronic Resource
English
Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection
British Library Conference Proceedings | 2004
|Boosting histograms of descriptor distances for scalable multiclass specific scene recognition
British Library Online Contents | 2011
|