PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Joint Cascade Optimization Using a Product Of Boosted Classifiers
Leonidas Lefakis and Francois Fleuret
In: NIPS 2010(2010).


The most standard strategy for efficient object detection consists of building a cascade composed of several binary classifiers. The detection process takes the form of a lazy evaluation of the conjunction of the responses of these classifiers, and concentrates the computation on difficult parts of the image which can not be trivially rejected. We introduce a novel strategy to construct jointly the classifiers of such a cascade. We interpret the response of a classifier as a probability of a positive prediction, and the overall response of the cascade as the probability that all the predictions are positive. From this noisy-AND model, we derive a consistent loss and a Boosting procedure to optimize that global probability on the training set. Such a joint learning allows the individual predictors to focus on a more restricted modeling problem, and improves the performance compared to a standard cascade. We demonstrate the efficiency of this approach on face and pedestrian detection with standard data-sets and comparisons with reference baselines.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:7327
Deposited By:Francois Fleuret
Deposited On:17 March 2011