Conservative visual learning for object detection with minimal hand labeling effort

We present a novel framework for unsupervised training of an object detection system. The basic idea is to (1) exploit a huge amount of unlabeled video data by being very conservative in selecting training examples; and (2) to start with a very simple object detection system and using generative and discriminative classifiers in an iterative co- training fashion arriving at a better object detector. We demonstrate the framework on a surveillance task where we learn a person detector. We start with a simple moving object classiffier and proceed with a robust PCA (on shape and appearance) as a generative classiffier which in turn generates a training set for a discriminative AdaBoost classiffier. The results obtained by AdaBoost are again filtered by PCA which produces an even better training set. We demonstrate that by using this approach we avoid hand labeling training data and still achieve a state of the art detection rate.