This repository contains PyTorch evaluation code, training code and pretrained models for SimMatchV2. Most of the code in this repository is adapt from here.
For details see SimMatchV2: Semi-Supervised Learning with Graph Consistency by Mingkai Zheng, Shan You, Lang Huang, Chen Luo, Fei Wang, Chen Qian, and Chang Xu
To run the code, you probably need to change the Dataset setting (ImagenetPercent function in data/imagenet.py), and Pytorch DDP setting (dist_init function in utils/dist_utils.py) for your server environment.
The distributed training of this code is based on slurm environment, we have provided the training scrips in script/train.sh
We also provide the pre-trained model.
| Arch | Setting | Epochs | Accuracy | Download | |
|---|---|---|---|---|---|
| SimMatchV2 | ResNet50 | 1% | 300 | 71.9 % | 300ep-res50-1p.pth |
| SimMatchV2 | ResNet50 | 10% | 300 | 76.2 % | 300ep-res50-10p.pth |
If you want to test the pre-trained model, please download the weights from the link above, and move them to the checkpoints folder. The evaluation scripts also have been provided in script/train.sh
If you find that SimMatch interesting and help your research, please consider citing it:
@InProceedings{Zheng_2022_CVPR,
author = {Zheng, Mingkai and You, Shan and Huang, Lang and Wang, Fei and Qian, Chen and Xu, Chang},
title = {SimMatch: Semi-Supervised Learning With Similarity Matching},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {14471-14481}
}
@InProceedings{Zheng_2023_ICCV,
author = {Zheng, Mingkai and You, Shan and Huang, Lang and Luo, Chen and Wang, Fei and Qian, Chen and Xu, Chang},
title = {SimMatchV2: Semi-Supervised Learning with Graph Consistency},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2023},
pages = {16432-16442}
}