Weighted boxes fusion: Ensembling boxes from different object detection models
This method improves object detection accuracy for computer vision applications, but it is incremental as it builds on existing ensembling techniques.
The authors tackled the problem of combining predictions from different object detection models by introducing weighted boxes fusion, which uses confidence scores to average bounding boxes, achieving top results on Open Images and COCO datasets.
In this work, we present a novel method for combining predictions of object detection models: weighted boxes fusion. Our algorithm utilizes confidence scores of all proposed bounding boxes to constructs the averaged boxes. We tested method on several datasets and evaluated it in the context of the Open Images and COCO Object Detection tracks, achieving top results in these challenges. The source code is publicly available at https://github.com/ZFTurbo/Weighted-Boxes-Fusion