Weighted boxes fusion: Ensembling boxes from different object detection models

By Roman A. Solovyev, Weimin Wang, Tatiana Gabruseva. Image and Vision Computing, 2021

503 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2765484bdd3e5d8674917efc98145daa1a71e9fa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xingkui Zhu
2. Qi Zhao
3. Xu Wang
4. Shuchang Lyu

In Computer Vision and Pattern Recognition

1. Xingkui Zhu
2. Qi Zhao
3. Xu Wang
4. Shuchang Lyu
5. Jianbing Shen
6. Wenguan Wang

Citations in the corpus

• TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios (2021, methodology): “On different models, we perform the same ms-testing operation and fuse the final five predictions by WBF to get the final result.”
• Object Detection in 20 Years: A Survey (2019, unknown): “object relationships and their spatial layout [118], [119].”
• A Training-Free Approach to Long-Tail Object Detection for Autonomous Driving (2026, unknown): “These detections are aggregated via Weighted Boxes Fusion (WBF) [19].”