Weighted boxes fusion: Ensembling boxes from different object detection models

Code

• github.com/ZFTurbo/Weighted-Boxes-Fusion
  OfficialIn papernone★ 0
• github.com/HirataYurina/yolov4-tiny-keras
  tf★ 16
• github.com/huyhieupham/learning-from-multiple-annotators
  pytorch★ 6
• github.com/Luckygyana/Invo-AI
  pytorch★ 3
• github.com/phykn/film-defect-detection
  pytorch★ 1
• github.com/grandoba/detectron2_ensemble
  pytorch★ 0
• github.com/HirataYurina/yoloV4-keras-techi
  tf★ 0
• github.com/FicmillaR/FicmillaR.github.io
  none★ 0
• github.com/HirataYurina/yoloV3-keras-sibyl
  tf★ 0
• github.com/Wastoon/MOT-CenterNet
  pytorch★ 0

Abstract

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

Tasks

Reproductions