Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# CMA-ckpt
|
| 2 |
+
|
| 3 |
+
Welcome to the repository for the CMA model, fine-tuned on the Imagenet-1k dataset.
|
| 4 |
+
|
| 5 |
+
## Quick Links
|
| 6 |
+
|
| 7 |
+
- [**Website**](https://github.com/ma-kjh/CMA-OoDD): The landing page for CMA-OoDD
|
| 8 |
+
- [**arXiv Paper**](https://arxiv.org/abs/2503.18817): Detailed information about the CMA-OoDD.
|
| 9 |
+
- [**GitHub Repository**](https://github.com/ma-kjh/CMA-OoDD?tab=readme-ov-file): Access the source code, fine-tuning scripts.
|
| 10 |
+
|
| 11 |
+
## Citing Our Work
|
| 12 |
+
|
| 13 |
+
If you find our codebase and dataset beneficial, please cite our work:
|
| 14 |
+
```
|
| 15 |
+
@article{kim2025enhanced,
|
| 16 |
+
title={Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations},
|
| 17 |
+
author={Kim, Jeonghyeon and Hwang, Sangheum},
|
| 18 |
+
journal={arXiv preprint arXiv:2503.18817},
|
| 19 |
+
year={2025}
|
| 20 |
+
}
|
| 21 |
+
```
|