BANA
This is the implementation of the paper "Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation".
For more information, please checkout the project site [website] and the paper [arXiv].
Requirements
- Python >= 3.6
- PyTorch >= 1.3.0
- yacs (https://github.com/rbgirshick/yacs)
Getting started
The folder data should be like this
data
└── VOCdevkit
└── VOC2012
├── JPEGImages
├── SegmentationClassAug
├── Annotations
├── ImageSets
├── BgMaskfromBoxes
└── Generation
├── Y_crf
└── Y_ret
git clone https://github.com/cvlab-yonsei/BANA.git
cd BANA
python stage1.py --config-file configs/stage1.yml --gpu-id 0 # For training a classification network
python stage2.py --config-file configs/stage2.yml --gpu-id 0 # For generating pseudo labels
Download our pseudo labels
- PASCAL VOC 2012 [Google Drive]
Bibtex
@inproceedings{oh2021background,
title = {Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation},
author = {Oh, Youngmin and Kim, Beomjun and Ham, Bumsub},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021},
}
28 Dec 30, 2022
![[CVPR 21] Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.](https://github.com/AyanKumarBhunia/Self-Supervised-Learning-for-Sketch/raw/main/sample_images/outline.png)
44 Dec 12, 2022
75 Dec 28, 2022
367 Dec 27, 2022
109 Dec 23, 2022
184 Dec 11, 2022
129 Dec 16, 2022
58 Dec 17, 2022
9 Nov 14, 2022
173 Dec 21, 2022
91 Dec 17, 2022
215 Jan 6, 2023
37 Dec 6, 2022
1.5k Dec 28, 2022
70 Nov 22, 2022
250 Jan 6, 2023
173 Dec 30, 2022
76 Jan 2, 2023
149 Jan 8, 2023