arxivst stuff from arxiv that you should probably bookmark

Mask R-CNN—new state of the art in image segmentation

Post · Mar 21, 2017 19:03 ·

state-of-the-art image segmentation instance segmentation CNN deep learning

Need a simple and flexible model that gives competitive results out-of-the-box? Try Mask R-CNN. An extension of Faster R-CNN, this network beats top results on all three tracks on the COCO suit of challenges.

Arxiv Abstract

  • Kaiming He
  • Georgia Gkioxari
  • Piotr Dollár
  • Ross Girshick

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.

Read the paper (pdf) »