mask rcnn算法原理图_DL之MaskR-CNN：Mask R-CNN算法的简介、架构详解、案例应用等配图集合之详细攻略...

DL之MaskR-CNN：Mask R-CNN算法的简介(论文介绍)、架构详解、案例应用等配图集合之详细攻略

目录

Mask R-CNN算法的简介(论文介绍)

Mask R-CNN是一种实例分割的方法。

Abstract

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, boundingbox object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code has been made available at: https://github.com/ facebookresearch/Detectron.

我们提出了一个概念简单、灵活和通用的对象实例分割框架。我们的方法有效地检测图像中的对象，同时为每个实例生成高质量的分割掩码。该方法称为Mask R-CNN，通过添加一个分支来预测一个对象掩码，与现有的用于边界框识别的分支并行，从而扩展了更快的R-CNN。Mask R-CNN训练简单，只增加了一个小开销到更快的R-CNN，运行在5帧每秒。此外，Mask R-CNN很容易推广到其他任务，例如，允许我们在相同的框架下估计人类的姿态。我们展示了COCO套件中所有三个方面的顶级结果，包括实例分割、边界框对象检测和人员关键点检测。没有华丽的点缀，Mask R-CNN在每个任务上都比所有现有的单模型条目表现得更好，包括COCO 2016挑战赛冠军。我们希望我们的简单而有效的方法将作为一个坚实的基线，并有助于简化未来在实例级识别方面的研究。代码已提供:https://github.com/facebookresearch /Detectron。

论文

Kaiming He Georgia GkioxariPiotr DollárRoss Girshick.

Mask R-CNN. ICCV, 2017

https://arxiv.org/abs/1703.06870

0、实验结果

1、实例分割掩码AP在COCO test-dev上Instance segmentation mask AP on COCO test-devMask R-CNN，采用ResNeXt-101-FPN骨干网络时，AP可以达到37.1，效果最好！​

raft-node="block" data-draft-type="table" data-size="normal" data-row-style="normal">Instance segmentation mask AP on