Weighted boxes fusion: Ensembling boxes from different object detection models

作者：

Highlights：

• Novel method was proposed for combining predictions in ensembles of different object detection models.

• Method significantly improves the quality of the fused predicted rectangles for an ensemble. The code is available at GitHub.

• Method was tested on several datasets and evaluated in the context of the Open Images and COCO Object Detection challenges.

摘要

•Novel method was proposed for combining predictions in ensembles of different object detection models.•Method significantly improves the quality of the fused predicted rectangles for an ensemble. The code is available at GitHub.•Method was tested on several datasets and evaluated in the context of the Open Images and COCO Object Detection challenges.

论文关键词：Object detection,Computer vision,Deep learning

论文评审过程：Received 26 November 2020, Revised 12 January 2021, Accepted 14 January 2021, Available online 3 February 2021, Version of Record 12 February 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104117