[paper reading] C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection CVPR2019

标签：generate   app   generated   multi   ati   overlap   无法   子集   paper   

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

[paper reading] C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection CVPR2019

标签：generate   app   generated   multi   ati   overlap   无法   子集   paper   

原文地址：https://www.cnblogs.com/demian/p/10668677.html