Improve object detection by splitting up Intersection-over-Union (IoU)
Improve object detection by splitting up Intersection-over-Union (IoU)
Decoupled IoU Regression for Object Detection
arXiv paper abstract https://arxiv.org/abs/2202.00866v1
arXiv PDF paper https://arxiv.org/pdf/2202.00866v1.pdf
Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes.
... Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem.
... propose a novel Decoupled IoU Regression (DIR) model to ... decouples the traditional localization confidence metric IoU into two new metrics, Purity and Integrity.
Purity reflects the proportion of the object area in the detected bounding box, and Integrity refers to the completeness of the detected object area.
Separately predicting Purity and Integrity ... The proposed DIR can be conveniently integrated with existing two-stage detectors and significantly improve their performance.
... obtain 51.3% AP on MS COCO benchmark, which outperforms previous methods and achieves state-of-the-art.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments