https://github.com/sayakpaul/adamatch-tf

Includes additional materials for the following keras.io blog post.
https://github.com/sayakpaul/adamatch-tf

keras semi-supervised-learning tensorflow unsupervised-domain-adaptation vision weak-supervision

Last synced: 18 days ago
JSON representation

Includes additional materials for the following keras.io blog post.

• Host: GitHub
• URL: https://github.com/sayakpaul/adamatch-tf
• Owner: sayakpaul
• License: apache-2.0
• Created: 2021-06-19T12:08:37.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-06-23T02:09:06.000Z (over 3 years ago)
• Last Synced: 2025-01-10T13:11:38.714Z (20 days ago)
• Topics: keras, semi-supervised-learning, tensorflow, unsupervised-domain-adaptation, vision, weak-supervision
• Language: Jupyter Notebook
• Homepage: https://keras.io/examples/vision/adamatch/
• Size: 1.07 MB
• Stars: 12
• Watchers: 3
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AdaMatch-TF

Includes additional materials for the following keras.io blog post: [Semi-supervision and domain adaptation with AdaMatch](https://keras.io/examples/vision/adamatch/).

## About the notebooks

* `AdaMatch.ipynb`: Original notebook submitted for the [PR](https://github.com/keras-team/keras-io/pull/513).

* `Vanilla_WideResNet.ipynb`: Trains a WideResNet-28-2 on MNIST (source domain) and evaluates on the SVHN dataset (target domain). The model trained in this notebook serves as the baseline. 

## Acknowledgements

* François Chollet for helping with the implementation.

* [ML-GDE](https://developers.google.com/programs/experts/) program for providing GCP credits that supported the experiments. 

## Paper citation

```

@misc{berthelot2021adamatch,

      title={AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation}, 

      author={David Berthelot and Rebecca Roelofs and Kihyuk Sohn and Nicholas Carlini and Alex Kurakin},

      year={2021},

      eprint={2106.04732},

      archivePrefix={arXiv},

      primaryClass={cs.LG}

}

```