DSLA: Dynamic smooth label assignment for efficient anchor-free object detection

Pattern Recognition(2022)

引用 12|浏览159
暂无评分
摘要
•The inconsistencies of classification and quality estimation are analyzed. Dynamic smooth label assignment is proposed to address the problems.•Interval relaxation strategy is proposed and combined with the improved centerness score. The assigned label is smoothed to a continuous value.•IoU score is dynamically calculated and coupled with the smooth label, resulting in dynamic smooth label.•DSLA is applied to popular anchor-free detectors. Comprehensive experiments are carried out on MS COCO to demonstrate the effectiveness.
更多
查看译文
关键词
Convolutional neural network,Object detection,Centerness score,Intersection-of-union
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要