Mask R-CNN
Mask R-CNN
复制标题
DOI：
10.1109/tpami.2018.2844175
复制
发表时间：
2020-02-01
影响因子：
23.6
通讯作者：
Girshick, Ross
中科院分区：
文献类型：
--
作者：
He, Kaiming;Gkioxari, Georgia;Girshick, Ross
我们提出了一个概念上简单、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模。该方法称为掩码R-CNN，通过在现有的边界框识别分支的基础上增加一个预测目标掩码的分支，从而扩展了更快的R-CNN。MASK R-CNN训练简单，只增加了较快的R-CNN很小的开销，运行速度为5fps。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中估计人体姿势。我们展示了COCO系列挑战中所有三个路径的顶级结果，包括实例分割、边界框对象检测和人关键点检测。在没有花哨的情况下，MASK R-CNN在每项任务上的表现都超过了所有现有的单一模型参赛作品，包括2016年可可挑战获胜者。我们希望我们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。代码已在以下网站上提供：https://github.com/facebookresearch/Detectron.
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, bounding-box 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.