A biased selection strategy for information recycling in Boosting cascade visual-object detectors

•Information recycling for boosting cascade detectors is systematically studied.•A biased selection strategy for weak classifier recycling is proposed.•The strategy is extended for recycling features and fully exploiting their power.•A more efficient visual-object detector is trained using the proposed technique.

We study the problem of information recycling in Boosting cascade visual-object detectors. It is believed that information obtained in the earlier stages of the cascade detector is also beneficial for the later stages, and that a more efficient detector can be constructed by recycling the existing information. In this work, we propose a biased selection strategy that promotes re-using existing information when selecting weak classifiers or features in each Boosting iteration. The strategy used can be interpreted as introducing a cardinality-based cost term to the Boosting loss function, and we solve the learning problem in a step-wise manner, similar to the gradient-Boosting scheme. Our work provides an alternative to the popular sparsity-inducing norms in solving such problems. Experimental results show that our method is superior to the existing methods.