Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- metric
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
### CROCScore
|
| 7 |
+
This is the CROCScore model from our publication `CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks`.
|
| 8 |
+
|
| 9 |
+
### Usage
|
| 10 |
+
For usage details, please view our repository at https://github.com/Gringham/CROC/tree/main.
|
| 11 |
+
|
| 12 |
+
### Citation
|
| 13 |
+
@misc{leiter2025crocevaluatingtrainingt2i,
|
| 14 |
+
title={CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks},
|
| 15 |
+
author={Christoph Leiter and Yuki M. Asano and Margret Keuper and Steffen Eger},
|
| 16 |
+
year={2025},
|
| 17 |
+
eprint={2505.11314},
|
| 18 |
+
archivePrefix={arXiv},
|
| 19 |
+
primaryClass={cs.CV},
|
| 20 |
+
url={https://arxiv.org/abs/2505.11314},
|
| 21 |
+
}
|
| 22 |
+
|
| 23 |
+
### Details
|
| 24 |
+
CROCScore is based on Phi4-Multimodal-Instruct (https://huggingface.co/microsoft/Phi-4-multimodal-instruct) that is released under MIT liecense (https://choosealicense.com/licenses/mit/).
|