etos-deepcut
A tool for object segmentation from extreme points.
About Deep Extreme Cut (DEXTR)
Visit project page for accessing the paper, and the pre-computed results.
This is based the implementation of Deep Extreme Cut (DEXTR), for object segmentation from extreme points.
Installation
-
Clone the repo:
git clone https://github.com/etosworld/etos-deepcut cd etos-deepcut -
Install dependencies:
pip install -r requirements.txt
-
Download the model by running the script inside
models/:cd models/ chmod +x download_dextr_model.sh ./download_dextr_model.sh cd ..
The default model is trained on PASCAL VOC Segmentation train + SBD (10582 images). To download models trained on PASCAL VOC Segmentation train or COCO, please visit project page, or keep scrolling till the end of this README.
-
To try the demo version of etos-deepcut, please run:
python demo.py
If installed correctly, the result should look like this:
image2txt
we have implemented the image2txt function , for each segmented object, an image and text file would be saved.enjoy!
Training
To train and evaluate etos-deepcut on PASCAL (or PASCAL + SBD), please follow these additional steps:
-
Install tensorboard (integrated with PyTorch).
pip install tensorboard tensorboardx
-
Download the pre-trained PSPNet model for semantic segmentation, taken from this repository.
cd models/ chmod +x download_pretrained_psp_model.sh ./download_pretrained_psp_model.sh cd ..
-
Set the paths in
mypath.py, so that they point to the location of PASCAL/SBD dataset. -
Run
python train_pascal.py, after changing the default parameters, if necessary (eg. gpu_id).
Enjoy!!
Pre-trained models
you can download the following DEXTR models, pre-trained on:
- PASCAL + SBD, trained on PASCAL VOC Segmentation train + SBD (10582 images). Achieves mIoU of 91.5% on PASCAL VOC Segmentation val.
- PASCAL, trained on PASCAL VOC Segmentation train (1464 images). Achieves mIoU of 90.5% on PASCAL VOC Segmentation val.
- COCO, trained on COCO train 2014 (82783 images). Achieves mIoU of 87.8% on PASCAL VOC Segmentation val.
TODO
- to support deep extreme video cut
Citation
@Inproceedings{Man+18,
Title = {Deep Extreme Cut: From Extreme Points to Object Segmentation},
Author = {K.K. Maninis and S. Caelles and J. Pont-Tuset and L. {Van Gool}},
Booktitle = {Computer Vision and Pattern Recognition (CVPR)},
Year = {2018}
}
@InProceedings{Pap+17,
Title = {Extreme clicking for efficient object annotation},
Author = {D.P. Papadopoulos and J. Uijlings and F. Keller and V. Ferrari},
Booktitle = {ICCV},
Year = {2017}
}