Skip to content
/ RIPU Public

[CVPR 2022 Oral] Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation https://arxiv.org/abs/2111.12940

License

Notifications You must be signed in to change notification settings

BIT-DA/RIPU

Repository files navigation


Region Impurity and Prediction Uncertainty (CVPR Oral)

Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu and Xinjing Cheng

Paper   Models   Bilibili   YouTube   Slides  

This repository provides the official code for the paper Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation.

🥳 We are happy to announce that RIPU was accepted at CVPR 2022 Oral Presentation.

Overview

We propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performance. Our algorithm, RIPU, introduces a new acquisition strategy characterizing the spatial adjacency of image regions along with the prediction confidence. The proposed region-based selection strategy makes more efficient use of a limited budget than image-based or point-based counterparts.

image

We show some qualitative examples from the Cityscapes validation set, image

and also visualize the queried regions to annotate. image

For more information on RIPU, please check our Paper.

Usage

Prerequisites

  • Python 3.7
  • Pytorch 1.7.1
  • torchvision 0.8.2

Step-by-step installation

conda create --name ADASeg -y python=3.7
conda activate ADASeg

# this installs the right pip and dependencies for the fresh python
conda install -y ipython pip

# this installs required packages
pip install -r requirements.txt

Data Preparation

Symlink the required dataset

ln -s /path_to_cityscapes_dataset datasets/cityscapes
ln -s /path_to_gtav_dataset datasets/gtav
ln -s /path_to_synthia_dataset datasets/synthia

Generate the label static files for GTAV/SYNTHIA Datasets by running

python datasets/generate_gtav_label_info.py -d datasets/gtav -o datasets/gtav/
python datasets/generate_synthia_label_info.py -d datasets/synthia -o datasets/synthia/

The data folder should be structured as follows:

├── datasets/
│   ├── cityscapes/     
|   |   ├── gtFine/
|   |   ├── leftImg8bit/
│   ├── gtav/
|   |   ├── images/
|   |   ├── labels/
|   |   ├── gtav_label_info.p
│   └──	synthia
|   |   ├── RAND_CITYSCAPES/
|   |   ├── synthia_label_info.p
│   └──	

Model Zoo

We have put our model checkpoints here [Google Drive] [百度网盘] (提取码RIPU).

GTAV to Cityscapes

name backbone budget mIoU ckpt where in Our Paper
1 RIPU-PA V2 40 px 65.5 Google Drive / BaiDu  Table 1
2 RIPU-RA V2 2.2% 69.6 Google Drive / BaiDu  Table 1
3 RIPU-RA V3+ 5.0% 71.2 Google Drive / BaiDu  Table 1

SYNTHIA to Cityscapes

name backbone budget mIoU ckpt where in Our Paper
1 RIPU-PA V2 40 px 66.1 Google Drive / BaiDu  Table 2
2 RIPU-RA V2 2.2% 70.1 Google Drive / BaiDu  Table 2
3 RIPU-RA V3+ 5.0% 71.4 Google Drive / BaiDu  Table 2

Source-free scenarios

task budget mIoU source pre-trained ckpt adapted ckpt Where in Our Paper
1 GTAV to Cityscapes 2.2% 67.1 Google Drive / BaiDu  Google Drive / BaiDu  Table 12
2 SYNTHIA to Cityscapes 2.2% 68.7 Google Drive / BaiDu  Google Drive / BaiDu  Table 13

RIPU Training

We provide the training scripts in scripts/ using a single GPU.

# training for GTAV to Cityscapes
sh gtav_to_cityscapes.sh

# training for SYNTHIA to Cityscapes
sh synthia_to_cityscapes.sh

RIPU Testing

To evaluate RIPU e.g. GTAV to Cityscapes (v3+, 5.0%), use the following command:

python test.py -cfg configs/gtav/deeplabv3plus_r101_RA.yaml resume checkpint/v3plus_gtav_ra_5.0_precent/model_last.pth OUTPUT_DIR checkpint/v3plus_gtav_ra_5.0_precent

Acknowledgements

This project is based on the following open-source projects: FADA and SDCA. We thank their authors for making the source code publically available.

Citation

If you find this project useful in your research, please consider citing:

@InProceedings{xie2022ripu,
    author    = {Xie, Binhui and Yuan, Longhui and Li, Shuang and Liu, Chi Harold and Cheng, Xinjing},
    title     = {Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {8068-8078}
}

Contact

If you have any problem about our code, feel free to contact

or describe your problem in Issues.

About

[CVPR 2022 Oral] Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation https://arxiv.org/abs/2111.12940

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published