Skip to content
Branch: master
Find file History
ppwwyyxx and facebook-github-bot ROIHeads: pass all features to heads
Summary: This relaxes the assumption that all heads take the same backbone features.

Reviewed By: rbgirshick

Differential Revision: D19945305

fbshipit-source-id: f1a4d428931182b16f148194927d131d883a5371
Latest commit 978e1df Feb 19, 2020
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
configs/InstanceSegmentation LVIS cocofied evaluation Feb 18, 2020
point_rend ROIHeads: pass all features to heads Feb 19, 2020
README.md LVIS cocofied evaluation Feb 18, 2020
train_net.py LVIS cocofied evaluation Feb 18, 2020

README.md

PointRend: Image Segmentation as Rendering

Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick

[arXiv] [BibTeX]


In this repository, we release code for PointRend in Detectron2. PointRend can be flexibly applied to both instance and semantic (comming soon) 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 visualisations 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 224×224 36.2 39.7 164254221 model | metrics
PointRend R50-FPN 224×224 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 224×224 35.9 164255101 model | metrics

Semantic Segmentation

[comming soon]

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}
}
You can’t perform that action at this time.