Data level object detector adaptation with online multiple instance samples

In object detection, the offline trained detector´s performance may be degraded in a particular deployed environment, because of the large variation of different environments. In this work, we propose a data level object detector adaptation method to new environments. By recording a small amount of offline data, it´s fully compatible with offline training method and easy to implement. We re-derive an efficient MILBoost by eliminating line search in optimization and introduce it to collect online multiple instance samples, which don´t require strict sample alignment. Experiment results with the human detector on public datasets illustrate the effectiveness of the proposed adaptation method. The adapted detector has good adaptation ability, while maintaining its generalization ability as well.