MIL陷入局部最优,检测到局部,无法完整的检测到物体。将instance划分为空间相关和类别相关的子集。在这些子集中定义一系列平滑的损失近似代替原损失函数,优化这些平滑损失。
C-MIL learns instance subsets, where the instances are spatially related, i.e., overlapping with each other, and class related, i.e., having similar object class scores.
C-MIL treats images as bags and image regions generated by an object proposal method [24,32] as instances
原文地址:https://www.cnblogs.com/demian/p/10668677.html
时间: 2024-10-29 03:02:45