091-revisiting-weak-to-strong-consistency-in-semi-supervised-semantic-segmentation

https://github.com/szu-advtech-2023/091-revisiting-weak-to-strong-consistency-in-semi-supervised-semantic-segmentation

Science Score: 18.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: SZU-AdvTech-2023
  • Language: Python
  • Default Branch: main
  • Size: 543 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Citation

https://github.com/SZU-AdvTech-2023/091-Revisiting-Weak-to-Strong-Consistency-in-Semi-Supervised-Semantic-Segmentation/blob/main/

## Getting Started


### Installation

```bash
conda create -n adaptunimatch python=3.10.4
conda activate adaptunimatch
pip install -r requirements.txt
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
```

### Pretrained Backbone

[ResNet-50](https://drive.google.com/file/d/1mqUrqFvTQ0k5QEotk4oiOFyP6B9dVZXS/view?usp=sharing) | [ResNet-101](https://drive.google.com/file/d/1Rx0legsMolCWENpfvE2jUScT3ogalMO8/view?usp=sharing) | [Xception-65](https://drive.google.com/open?id=1_j_mE07tiV24xXOJw4XDze0-a0NAhNVi)

```
 ./pretrained
     resnet50.pth
     resnet101.pth
     xception.pth
```

### Dataset

- Pascal: [JPEGImages](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar) | [SegmentationClass](https://drive.google.com/file/d/1ikrDlsai5QSf2GiSUR3f8PZUzyTubcuF/view?usp=sharing)

Please modify your dataset path in configuration files.

## Usage

### AdaptUniMatch

```bash
# use torch.distributed.launch
sh scripts/train.sh  
# to fully reproduce our results, the  should be set as 4 on all three datasets
# otherwise, you need to adjust the learning rate accordingly

# or use slurm
# sh scripts/slurm_train.sh   
```

To train on other datasets or splits, please modify
``dataset`` and ``split`` in [train.sh](https://github.com/LiheYoung/UniMatch/blob/main/scripts/train.sh).

Owner

  • Name: SZU-AdvTech-2023
  • Login: SZU-AdvTech-2023
  • Kind: organization

Citation (citation.txt)

@inproceedings{REPO091,
    author = "Yang, Lihe and Qi, Lei and Feng, Litong and Zhang, Wayne and Shi, Yinghuan",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
    pages = "7236--7246",
    title = "{Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation}",
    year = "2023"
}

GitHub Events

Total
Last Year