M2YOLOF: Based on effective receptive fields and multiple-in-single-out encoder for object detection
Expert Systems with Applications(2023)
摘要
•The proposed M2YOLOF detects objects on one feature map and performs well on small objects.•The detection speed of our method is as fast as YOLOF, but more accurate.•Designing a Multi-in-Single-out attention encoder to improve representation from backbone.•Designing a dynamic sample selection method in combination with effective receptive fields.
更多查看译文
关键词
Object detection,Deep learning,YOLOF,Effective receptive field
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