Weighted Boxes Fusion: ensembling boxes for object detection models

In this work, we introduce a novel Weighted Box Fusion (WBF) ensembling algorithm that boosts the performance by ensembling predictions from different object detection models. Method was tested on predictions of different models trained on large Open Images Dataset. The source code for our approach is publicly available at https://github.com/ZFTurbo/Weighted-Boxes-Fusion