Mask R-CNN
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.
Categories
- MaskRCNN:Paper: 논문 번역.
- MaskRCNN:Example:VideoReadWrite - Mask R-CNN 데모를 위한 Video Read & Write Python example.
- MaskRCNN:Example:ExcelReport - Mask R-CNN 결과 리포팅을 Excel파일로 출력한다.
- Detectron2#Logging fields - 훈련 후 로깅파일을 텐서보드로 확인했을 때 각 그래프 보는 방법.
Documentation
- Mask R-CNN
- https://arxiv.org/abs/1703.06870
-
1703.06870.pdf
Implementation
- Keras implementation of MaskRCNN object detection.
- https://github.com/fizyr/keras-maskrcnn
- Faster R-CNN and Mask R-CNN in PyTorch 1.0 (maskrcnn-benchmark)
- facebook research
- Mask R-CNN for Object Detection and Segmentation (Keras and TensorFlow)
- https://github.com/matterport/Mask_RCNN
See also
- Faster R-CNN
- Object Recognition
- Path Aggregation Network for Instance Segmentation (PANet)
- Instance segmentation
- Semantic Segmentation
- Detectron
- Detectron2
- RetainNet
- RetinaMask
- Fully Convolutional One-Stage Object Detection (FCOS)
- Mask Scoring R-CNN (MS R-CNN)
- TensorMask
- Mesh R-CNN
- Mask2Former - Masked-RCNN 에 Transformer 붙인 느낌?
Favorite site
- From R-CNN to Mask R-CNN
- [추천] sogangori - MASK R-CNN 1
- Mask R-CNN | TensorMSA
- (번역글) Image Segmentation에 대한 짧은 이야기: R-CNN 에서 부터 Mask R-CNN 까지
- Mask R-CNN | TensorMSA
- MASK R-CNN - 명상 : 네이버 블로그
- CNN을 활용한 주요 Model - (4) : Semantic Segmentation
- 1편: Semantic Segmentation 첫걸음!
Project site
- Github - Mask R-CNN project site (Keras and TensorFlow)
- Github - CharlesShang/FastMaskRCNN TensorFlow
- Github - roytseng-tw/Detectron.pytorch
Guide
References
-
Sogangori_-MASK_R-CNN-_Review.pdf ↩