# Frequency Distribution Loss (FDL) for misaligned data
**The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024**
[Zhangkai Ni](https://eezkni.github.io/), [Juncheng Wu](https://scholar.google.com/citations?user=RSn2gykAAAAJ&hl=en&oi=sra), [Zian Wang](https://scholar.google.com/citations?user=Mi6YUBoAAAAJ&hl=en&oi=sra), [Wenhan Yang](https://flyywh.github.io/), [Hanli Wang](https://mic.tongji.edu.cn/51/91/c9778a86417/page.htm), [Lin Ma](https://forestlinma.com/)
This repository provides the official PyTorch implementation for the paper “Misalignment-Robust Frequency Distribution Loss for Image Transformation”, CVPR-2024. [Paper](https://arxiv.org/abs/2402.18192)
## About FDL
A novel Frequency Distribution Loss (FDL) for image transformation models trained with misaligned data, opening up new avenues for addressing the broad issue of misalignment in image transformation tasks.
## Quick Start
### Installation:
`pip install fdl-pytorch`
### Requirements:
- Python>=3.6
- Pytorch>=1.0
### Usage:
```python
from FDL_pytorch import FDL_loss
fdl_loss = FDL_loss()
# X: (N,C,H,W)
# Y: (N,C,H,W)
loss_value = fdl_loss(X, Y)
loss_value.backward()
```
## Citation
If you find our work useful, please cite it as
```
@article{ni2024misalignment,
title={Misalignment-Robust Frequency Distribution Loss for Image Transformation},
author={Ni, Zhangkai and Wu, Juncheng and Wang, Zian and Yang, Wenhan and Wang, Hanli and Ma, Lin},
journal={arXiv preprint arXiv:2402.18192},
year={2024}
}
```
## Contact
Thanks for your attention! If you have any suggestion or question, feel free to leave a message here or contact Dr. Zhangkai Ni (eezkni@gmail.com).
## License
[MIT License](https://opensource.org/licenses/MIT)
Raw data
{
"_id": null,
"home_page": "https://github.com/eezkni/FDL",
"name": "FDL-pytorch",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "pytorch,loss,image transformation,misalignment",
"author": "Zhangkai Ni, Juncheng Wu, Zian Wang",
"author_email": "zkni@tongji.edu.cn",
"download_url": "https://files.pythonhosted.org/packages/56/7f/800b3693e970adf456e35f832c4518aa8b6cf6a90da6fcab6b57a6ed8535/FDL_pytorch-1.0.tar.gz",
"platform": "python",
"description": "# Frequency Distribution Loss (FDL) for misaligned data\n\n**The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024**\n\n[Zhangkai Ni](https://eezkni.github.io/), [Juncheng Wu](https://scholar.google.com/citations?user=RSn2gykAAAAJ&hl=en&oi=sra), [Zian Wang](https://scholar.google.com/citations?user=Mi6YUBoAAAAJ&hl=en&oi=sra), [Wenhan Yang](https://flyywh.github.io/), [Hanli Wang](https://mic.tongji.edu.cn/51/91/c9778a86417/page.htm), [Lin Ma](https://forestlinma.com/)\n\nThis repository provides the official PyTorch implementation for the paper \u201cMisalignment-Robust Frequency Distribution Loss for Image Transformation\u201d, CVPR-2024. [Paper](https://arxiv.org/abs/2402.18192)\n\n## About FDL\n\nA novel Frequency Distribution Loss (FDL) for image transformation models trained with misaligned data, opening up new avenues for addressing the broad issue of misalignment in image transformation tasks.\n\n## Quick Start\n\n### Installation:\n\n`pip install fdl-pytorch`\n\n### Requirements:\n\n- Python>=3.6\n- Pytorch>=1.0\n\n### Usage:\n\n```python\nfrom FDL_pytorch import FDL_loss\nfdl_loss = FDL_loss()\n# X: (N,C,H,W) \n# Y: (N,C,H,W) \nloss_value = fdl_loss(X, Y)\nloss_value.backward()\n```\n\n## Citation\n\nIf you find our work useful, please cite it as\n\n```\n@article{ni2024misalignment,\n title={Misalignment-Robust Frequency Distribution Loss for Image Transformation},\n author={Ni, Zhangkai and Wu, Juncheng and Wang, Zian and Yang, Wenhan and Wang, Hanli and Ma, Lin},\n journal={arXiv preprint arXiv:2402.18192},\n year={2024}\n}\n```\n\n## Contact\n\nThanks for your attention! If you have any suggestion or question, feel free to leave a message here or contact Dr. Zhangkai Ni (eezkni@gmail.com).\n\n\n## License\n\n[MIT License](https://opensource.org/licenses/MIT)\n\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Frequency Distribution Loss (FDL) for misalignment data",
"version": "1.0",
"project_urls": {
"Homepage": "https://github.com/eezkni/FDL"
},
"split_keywords": [
"pytorch",
"loss",
"image transformation",
"misalignment"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "bd8c74e0d0937434f9229105ac7032d1b54422db701ea69ac223090d42a10aa4",
"md5": "347885c221954e146824c820df264f2c",
"sha256": "78621ebe88eafc98c5302bc9bc0a035359d3ca5e0c500b5440938c049911d1c3"
},
"downloads": -1,
"filename": "FDL_pytorch-1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "347885c221954e146824c820df264f2c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 4643,
"upload_time": "2024-03-09T13:44:59",
"upload_time_iso_8601": "2024-03-09T13:44:59.174987Z",
"url": "https://files.pythonhosted.org/packages/bd/8c/74e0d0937434f9229105ac7032d1b54422db701ea69ac223090d42a10aa4/FDL_pytorch-1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "567f800b3693e970adf456e35f832c4518aa8b6cf6a90da6fcab6b57a6ed8535",
"md5": "1bf5d3ca51e2a46621741238b384bb01",
"sha256": "df7494c5b4f5cbeb68b8166f93fcb2b92a600703f4538445c9de58a47e9c5f69"
},
"downloads": -1,
"filename": "FDL_pytorch-1.0.tar.gz",
"has_sig": false,
"md5_digest": "1bf5d3ca51e2a46621741238b384bb01",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 4595,
"upload_time": "2024-03-09T13:45:00",
"upload_time_iso_8601": "2024-03-09T13:45:00.343040Z",
"url": "https://files.pythonhosted.org/packages/56/7f/800b3693e970adf456e35f832c4518aa8b6cf6a90da6fcab6b57a6ed8535/FDL_pytorch-1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-09 13:45:00",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "eezkni",
"github_project": "FDL",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "fdl-pytorch"
}
JSON
