Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 138363239 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 138363294 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 144219035 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 138205316 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 137259246 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 137849525 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 142202221 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 137260150 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 137849551 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 137260431 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 144219072 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 137849600 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNet |
---|---|
ID | 142423278 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNeXt |
---|---|
ID | 144219108 |
SHOW MORE |
Architecture | Convolution, RoIAlign, Softmax, RPN, Dense Connections, ResNeXt |
---|---|
ID | 139653917 |
SHOW MORE |
Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. In principle, Mask R-CNN is an intuitive extension of Faster R-CNN, but constructing the mask branch properly is critical for good results.
Most importantly, Faster R-CNN was not designed for pixel-to-pixel alignment between network inputs and outputs. This is evident in how RoIPool, the de facto core operation for attending to instances, performs coarse spatial quantization for feature extraction. To fix the misalignment, Mask R-CNN utilises a simple, quantization-free layer, called RoIAlign, that faithfully preserves exact spatial locations.
There are several Mask R-CNN models available in Detectron2, with different backbones and learning schedules.
To load from the Detectron2 model zoo:
from detectron2 import model_zoo
model = model_zoo.get("COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml", trained=True)
Replace the configuration path with the variant you want to use. You can find the paths in the model summaries at the top of this page.
You can follow the Getting Started guide on Colab to see how to train a model.
You can also read the official Detectron2 documentation.
@misc{wu2019detectron2,
author = {Yuxin Wu and Alexander Kirillov and Francisco Massa and
Wan-Yen Lo and Ross Girshick},
title = {Detectron2},
howpublished = {\url{https://github.com/facebookresearch/detectron2}},
year = {2019}
}
MODEL | BOX AP |
---|---|
Mask R-CNN (X101-FPN, 3x) | 44.3 |
Mask R-CNN (R101-FPN, 3x) | 42.9 |
Mask R-CNN (R101-C4, 3x) | 42.6 |
Mask R-CNN (R101-DC5, 3x) | 41.9 |
Mask R-CNN (R50-FPN, 3x) | 41.0 |
Mask R-CNN (R50-DC5, 3x) | 40.0 |
Mask R-CNN (R50-C4, 3x) | 39.8 |
Mask R-CNN (R50-FPN, 1x) | 38.6 |
Mask R-CNN (R50-DC5, 1x) | 38.3 |
Mask R-CNN (R50-C4, 1x) | 36.8 |
MODEL | MASK AP |
---|---|
Mask R-CNN (X101-FPN, 3x) | 39.5 |
Mask R-CNN (R101-FPN, 3x) | 38.6 |
Mask R-CNN (R101-DC5, 3x) | 37.3 |
Mask R-CNN (R50-FPN, 3x) | 37.2 |
Mask R-CNN (R101-C4, 3x) | 36.7 |
Mask R-CNN (R50-DC5, 3x) | 35.9 |
Mask R-CNN (R50-FPN, 1x) | 35.2 |
Mask R-CNN (R50-C4, 3x) | 34.4 |
Mask R-CNN (R50-DC5, 1x) | 34.2 |
Mask R-CNN (R50-C4, 1x) | 32.2 |
MODEL | AP50 | BOX AP |
---|---|---|
Mask R-CNN (R50-C4, VOC) | 80.3 | 51.9 |
MODEL | MASK AP |
---|---|
Mask R-CNN (R50-FPN, Cityscapes) | 36.5 |