文件名称：ICCV2019.pdf
文件大小：7.88MB
文件格式：PDF
更新时间：2023-06-19 07:51:35
弱监督目标检测
It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations. Most existing methods tend to solve this problem by using a two-phase learning procedure, i.e., multiple instance learning detector followed by a fully supervised learning detector with bounding-box regression. 更多内容加微信 ai_seer