Learning Non-Maximum Suppression

Jan Hosang, Rodrigo Benenson, Bernt Schiele; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4507-4515

Abstract


Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, fea tures, and the classifier becoming one neural network improved results two-fold on general object detection. One indispensable component is non-maximum suppression (NMS), a post-processing algorithm responsible for merging all detections that belong to the same object. The de facto standard NMS algorithm is still fully hand-crafted, suspiciously simple, and -- being based on greedy clustering with a fixed distance threshold -- forces a trade-off between recall and precision. We propose a new network architecture designed to perform NMS, using only boxes and their score. We report experiments for person detection on PETS and for general object categories on the COCO dataset. Our approach shows promise providing improved localization and occlusion handling.

Related Material


[pdf] [Supp] [arXiv] [poster] [video]
[bibtex]
@InProceedings{Hosang_2017_CVPR,
author = {Hosang, Jan and Benenson, Rodrigo and Schiele, Bernt},
title = {Learning Non-Maximum Suppression},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}