[经典网络]：Mask R-CNN 网络结构详解 : R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, FCN

论文：He, Kaiming, et al. “Mask r-cnn.” Proceedings of the IEEE international conference on computer vision. 2017.
代码：TensorFlow实现

实例分割模型Mask R-CNN详解：从R-CNN，Fast R-CNN，Faster R-CNN再到Mask R-CNN从R-CNN¹开讲讲到Mask R-CNN²，很完整，简明的表述了R-CNN系列的发展，但是不够细节。Mask R-CNN²可以理解为Faster R-CNN³ + FCN⁴

1. R-CNN²算法详解

a. 在图像中确定约1000-2000个候选框
b. 对于每个候选框内图像块，使用深度网络提取特征
c. 对候选框中提取出的特征，使用分类器判别是否属于一个特定类
d. 对于属于某一特征的候选框，用回归器进一步调整其位置

2. Fast R-CNN⁵算法详解

网络末端同步训练的分类和位置调整，提升准确度
使用多尺度的图像金字塔，性能几乎没有提高
倍增训练数据，能够有2%-3%的准确度提升
网络直接输出各类概率(softmax)，比SVM分类器性能略好
更多候选窗不能提升性能

3. Faster R-CNN³算法详解

目标检测的四个基本步骤（候选区域生成，特征提取，分类，位置精修）终于被统一到一个深度网络框架之内

4. Mask R-CNN算法详解
   
   输入图片进行特征提取，使用FPN⁶网络

[5]:Lin, Tsung-Yi, et al. “Feature pyramid networks for object detection.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.
参考：

---

1. Girshick, Ross, et al. “Rich feature hierarchies for accurate object detection and semantic segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. ↩︎

2. He, Kaiming, et al. “Mask r-cnn.” Proceedings of the IEEE international conference on computer vision. 2017. ↩︎ ↩︎ ↩︎

3. Ren, Shaoqing, et al. “Faster r-cnn: Towards real-time object detection with region proposal networks.” Advances in neural information processing systems. 2015. ↩︎ ↩︎

4. Long, Jonathan, Evan Shelhamer, and Trevor Darrell. “Fully convolutional networks for semantic segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. ↩︎

5. Girshick, Ross. “Fast r-cnn.” Proceedings of the IEEE international conference on computer vision. 2015. ↩︎

6. Lin, Tsung-Yi, et al. “Feature pyramid networks for object detection.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. ↩︎