Abstract

Classification cascades have been very effective for object detection. Such a cascade fails to perform well in data domains with variations in appearances that may not be captured in the training examples. This limited generalization severely restricts the  domains for which they can be used effectively. A common approach to address this limitation is to train a new cascade of classifiers from scratch for each of the new domains. Building separate detectors for each of the different domains requires huge annotation and computational effort, making it not scalable to a large number of data domains. Here we present an algorithm for quickly adapting a pre-trained cascade of classifiers -- using a small number of labeled positive instances from a different yet similar data domain. In our experiments with images of human babies and human-like characters from movies, we demonstrate that the adapted cascade significantly outperforms both the original cascade and the one trained from scratch using the given training examples.