Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Logo of CS4People

The Taub Faculty of Computer Science Events and Talks

Pixel Club: Hybrid Classifiers for Object Classification with a Rich Background
event speaker icon
Margarita Osadchy (Computer Science, Haifa University)
event date icon
Tuesday, 18.12.2012, 11:30
event location icon
EE Meyer Building 1061
The majority of current methods in object classification use the one-against-res​t training scheme. We argue that when applied to a large number of classes, this strategy is problematic: as the number of classes increases, the negative class becomes a very large and complicated collection of images. The resulting classification problem then becomes extremely unbalanced, and kernel SVM classifiers trained on such sets require long training time and are slow in prediction. To address these problems, we propose to consider the negative class as a background and characterize it by a prior distribution. Further, we propose to construct "hybrid" classifiers, which are trained to separate this distribution from the samples of the positive class. A typical classifier first projects (by a function which may be non-linear) the inputs to a one-dimensional space, and then thresholds this projection. Theoretical results and empirical evaluation suggest that, after projection, the background has a relatively simple distribution, which is much easier to parameterize and work with. Our results show that hybrid classifiers offer an advantage over SVM classifiers, both in performance and complexity, especially when the negative (background) class is large.