Awesome

L2RCLIP

The official implementation of the paper "Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification" is available.

<a href="https://arxiv.org/abs/2306.13856"><img src="https://img.shields.io/badge/arXiv-2306.13856-b31b1b.svg" height=22.5></a> <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" height=22.5></a>

Code is coming soon.

TODO

• Release the datalist used during training.
• Release the training code and inference code of Morph dataset.
• Release pre-trained models.

Acknowledgments

This codebase is from CLIP-ReID, CLIP and OrdinalEntropy.

What's More

Check out these amazing works leveraging CLIP for number/rank problems!

• OrdinalCLIP(NeurIPS22). Paper. Code.
• CrowdCLIP(CVPR23). Paper. Code.

Citation

If you use this code for your research, please cite our paper <a href="https://arxiv.org/abs/2306.13856">L2RCLIP: Boosting Language-Driven Ordering Alignment for Ordinal Classification</a>:

@article{wang2023learning,
  title={Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification},
  author={Wang, Rui and Li, Peipei and Huang, Huaibo and Cao, Chunshui and He, Ran and He, Zhaofeng},
  journal={arXiv preprint arXiv:2306.13856},
  year={2023}
}