Paper reading: Mask RCNN

Paper: Mask R-CNN

作者: Kaiming He Georgia Gkioxari Piotr Dollar Ross Girshick

摘要：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 tricks, 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 will be made available.

贡献：

• 基于Faster RCNN的框架，对于ROI增加了instance segmentation分支，利用pixel-to-pixel的mask，来帮助classification和regeression
• 改进了ROI，提出了ROI Align，对于segmentation的pixel-to-pixel可以对齐的更为准确。

细节：

• Mask
• ROI Align