Constrained Online Cut-Paste for Object Detection
IEEE Transactions on Circuits and Systems for Video Technology(2021)
摘要
Well-annotated training samples show necessity in achieving high performance of object detection, but collection of massive samples is extremely laborious and costly. Recently, cut-paste based methods show the potential to augment the training samples by cutting the foreground instances and pasting them on some background regions. However, existing cut-paste based methods hardly guarantee the qual...
更多查看译文
关键词
Switches,Training,Object detection,Detectors,Convergence,Coherence,Visualization
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要