TinyDet: accurately detecting small objects within 1 GFLOPs

Shaoyu Chen,Tianheng Cheng,Jiemin Fang,Qian Zhang,Yuan Li,Wenyu Liu,Xinggang Wang

SCIENCE CHINA-INFORMATION SCIENCES（2023）

引用 0|浏览46

暂无评分

摘要

Conclusion In this study, we propose a series of lightweight detectors named TinyDet. TinyDet is with good performance-computation trade-offs (30.3 mAP with only 991 MFLOPs) and applicable to resource-constrained mobile or edge devices. Besides, TinyDet is superior to other lightweight detectors in small object detection.

查看译文

关键词

small objects,tinydet,gflops

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