文章目录
- Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning(ICCV2023)
- Exploiting Temporal Context for Tiny Object Detection(WACV2023)
- ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector(CVPR2023)
- Efficient Classification of Very Large Images with Tiny Objects(CVPR2022)
- RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection(ECCV2022)
- Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection(CVPR2023)
- TOD-CMLNN(2023)
Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning(ICCV2023)
hh
解决了小目标训练样本不足质量低以及判别信息匮乏的问题
提出CFINet
引入了由粗到精的区域提议网络(CRPN)解决训练样本不足质量低的问题
添加了特征模仿FI分支,并设计了一个损失函数对其进行优化,提升模型对小目标的识别能力和表示效果。