Spaces:
Running
on
Zero
PointRend: Image Segmentation as Rendering
Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick
![](https://alexander-kirillov.github.io/images/kirillov2019pointrend.jpg)
In this repository, we release code for PointRend in Detectron2. PointRend can be flexibly applied to both instance and semantic segmentation tasks by building on top of existing state-of-the-art models.
Installation
Install Detectron 2 following INSTALL.md. You are ready to go!
Quick start and visualization
This Colab Notebook tutorial contains examples of PointRend usage and visualizations of its point sampling stages.
Training
To train a model with 8 GPUs run:
cd /path/to/detectron2/projects/PointRend
python train_net.py --config-file configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml --num-gpus 8
Evaluation
Model evaluation can be done similarly:
cd /path/to/detectron2/projects/PointRend
python train_net.py --config-file configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint
Pretrained Models
Instance Segmentation
COCO
Mask head |
Backbone | lr sched |
Output resolution |
mask AP |
mask AP* |
model id | download |
---|---|---|---|---|---|---|---|
PointRend | R50-FPN | 1Γ | 224Γ224 | 36.2 | 39.7 | 164254221 | model | metrics |
PointRend | R50-FPN | 3Γ | 224Γ224 | 38.3 | 41.6 | 164955410 | model | metrics |
AP* is COCO mask AP evaluated against the higher-quality LVIS annotations; see the paper for details. Run python detectron2/datasets/prepare_cocofied_lvis.py
to prepare GT files for AP* evaluation. Since LVIS annotations are not exhaustive lvis-api
and not cocoapi
should be used to evaluate AP*.
Cityscapes
Cityscapes model is trained with ImageNet pretraining.
Mask head |
Backbone | lr sched |
Output resolution |
mask AP |
model id | download |
---|---|---|---|---|---|---|
PointRend | R50-FPN | 1Γ | 224Γ224 | 35.9 | 164255101 | model | metrics |
Semantic Segmentation
Cityscapes
Cityscapes model is trained with ImageNet pretraining.
Method | Backbone | Output resolution |
mIoU | model id | download |
---|---|---|---|---|---|
SemanticFPN + PointRend | R101-FPN | 1024Γ2048 | 78.6 | 186480235 | model | metrics |
Citing PointRend
If you use PointRend, please use the following BibTeX entry.
@InProceedings{kirillov2019pointrend,
title={{PointRend}: Image Segmentation as Rendering},
author={Alexander Kirillov and Yuxin Wu and Kaiming He and Ross Girshick},
journal={ArXiv:1912.08193},
year={2019}
}