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

本文转载自查看原文 2019-04-14 23:52 643

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

待解决的问题：

1) How to optimize the non-convex function

2) How to perform instance selection in the early training stages when the instance selector is not well trained.

to be continue ...

更完整的论文笔记[csdn]

免责声明！

本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。

猜您在找 [ICCV 2019] Weakly Supervised Object Detection With Segmentation Collaboration 论文阅读笔记五十三：Libra R-CNN: Towards Balanced Learning for Object Detection(CVPR2019) [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural networks论文笔记 [CVPR2017] Deep Self-Taught Learning for Weakly Supervised Object Localization 论文笔记多示例学习 multiple instance learning (MIL) Paper Reading: Relation Networks for Object Detection 论文阅读笔记五十一：CenterNet: Keypoint Triplets for Object Detection(CVPR2019) 论文阅读笔记四十八：Bounding Box Regression with Uncertainty for Accurate Object Detection(CVPR2019) 论文阅读笔记五十七:FCOS: Fully Convolutional One-Stage Object Detection(CVPR2019) 论文阅读笔记五十二：CornerNet-Lite: Efficient Keypoint Based Object Detection（CVPR2019）