Non-Maximum Suppression
كبت غير أعظمي
تقنية معالجة لاحقة تزيل الاكتشافات المتداخلة الزائدة بالإبقاء فقط على الاكتشاف الأعلى درجة في كل مجموعة متداخلة.
A post-processing technique that removes redundant overlapping detections by keeping only the highest-scoring detection in each overlapping group.
Also translated asNMS، إزالة التكرارات، الكبت اللاأعظمي، تنقية تراكب إطارات الرصد البصري، عزل وإلغاء مربعات الإحاطة الزائدة
First appears in this corpus in: A Computational Approach to Edge Detection (1986)
Appears in these papers
- A Computational Approach to Edge Detection1986in the sky ✦
- A Computational Approach to Edge Detection1986in the sky ✦
- Microsoft COCO: Common Objects in Context2014in the sky ✦
- End-to-End Object Detection with Transformers2020in the sky ✦
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks2015in the sky ✦
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks2015in the sky ✦
- Feature Pyramid Networks for Object Detection2017in the sky ✦
- Histograms of Oriented Gradients for Human Detection2005in the sky ✦
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014in the sky ✦
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014in the sky ✦
- Focal Loss for Dense Object Detection2017in the sky ✦
- Focal Loss for Dense Object Detection2017in the sky ✦
- Segment Anything2023in the sky ✦
- SSD: Single Shot MultiBox Detector2016in the sky ✦
- SSD: Single Shot MultiBox Detector2016in the sky ✦
- You Only Look Once: Unified, Real-Time Object Detection2015in the sky ✦
- You Only Look Once: Unified, Real-Time Object Detection2015in the sky ✦
- YOLOv3: An Incremental Improvement2018in the sky ✦
- YOLOv3: An Incremental Improvement2018in the sky ✦