0 citations0 references

Learning Non-maximum Suppression

2017pp. 6469–6477

Citations Over TimeTop 1% of 2017 papers

Jan Hosang, Rodrigo Benenson, Bernt Schiele

Abstract

Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, features, 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 Papers

→ De Jure/De Facto Institutions(2019)2 cited
Legal Judgment of Real Property Registration and De Facto Right of Things(2013)
On Japanese De Facto Marriage(2007)
→ Conditions of accession in facto marriage(2017)
→ Sovereigns of England, de jure as well as de facto(1897)