Adaptive object detection by implicit sub-class sharing features

In this paper, we describe an adaptive object detection system based on boosted weak classifiers. We formulate the learning of object detection as to find the representative sharing features over the examples of object. Objects with low intra-class variation imply that more generic features for detection can be selected. In contrast, more specific features for only subset of examples should be encouraged to gain an elegant representation for the object with high intra-class variation. In this spirit, we implement an implicit partition over positive examples to obtain a data-driven clustering. Based on the implicit partition, we encourage an intra-class and inter-class feature sharing between sub-categories and build an adaptive hierarchical cascade of weak classifiers. Experimental results prove that the intra-class sharing makes an adaptive trade-off between performance and efficiency on various object detection tasks. The inter-class sharing allows objects to borrow semantic information from related well labeled objects. We hope that the proposed implicit feature sharing over sub-categories can extend the application of traditional boosting methods.

► A novel weak partition method keeps the balance between performance and efficiency in training.
► The structure of object detector can adapt to the intra-class variation of detection problem.
► The feature sharing over sub-categories can transfer the prior knowledge across classes.
► The transfer of knowledge improves the performance in multiclass object detection.