A Convnet for Non-maximum Suppression

Hosang, Jan and Benenson, Rodrigo and Schiele, Bernt
(2016) A Convnet for Non-maximum Suppression.
In: Pattern Recognition (GCPR 2016).

Full text not available from this repository.


Non-maximum suppression (NMS) is used in virtually all state-of-the-art object detection pipelines. While essential object detection ingredients such as features, classifiers, and proposal methods have been extensively researched surprisingly little work has aimed to systematically address NMS. The de-facto standard for NMS is based on greedy clustering with a fixed distance threshold, which forces to trade-off recall versus precision. We propose a convnet designed to perform NMS of a given set of detections. We report experiments on a synthetic setup, and results on crowded pedestrian detection scenes. Our approach overcomes the intrinsic limitations of greedy NMS, obtaining better recall and precision.


Actions (login required)

View Item View Item