---
license: apache-2.0
task_categories:
- image-classification
language:
- en
tags:
- medical
- biology
---
### Model Checkpoints and Logs
| Name                                                      | Few-Shot | Base-to-Novel |  
|-----------------------------------------------------------|:---------:|:----------:| 
| [**BiomedCoOp**](https://github.com/HealthX-Lab/BiomedCoOp/blob/main/trainers/BiomedCoOp/biomedcoop_biomedclip.py) |  [link](https://huggingface.co/TahaKoleilat/BiomedCoOp/tree/main/few_shot)  | [link](https://huggingface.co/TahaKoleilat/BiomedCoOp/tree/main/base2new) |

### Reproducing Results

Run the following scripts to use the checkpoints and get testing results. Note that the following scripts automatically download the desired model weights:

##### (1) Few-shot Evaluation

```bash
CUDA_VISIBLE_DEVICES=<GPU number> bash scripts/biomedcoop/eval_fewshot.sh <data directory> <dataset> <nb of shots>
# Example on BTMRI using 16 shots and the BiomedCLIP model on GPU 0
CUDA_VISIBLE_DEVICES=0 bash scripts/biomedcoop/eval_fewshot.sh data btmri 16
```

##### (2) Base-to-Novel Generalization

```bash
CUDA_VISIBLE_DEVICES=<GPU number> bash scripts/biomedcoop/eval_base2new.sh <data directory> <dataset> <nb of shots>
# Example on BTMRI using 16 shots and the BiomedCLIP model on GPU 0
CUDA_VISIBLE_DEVICES=0 bash scripts/biomedcoop/eval_base2new.sh data btmri 16
```

### Citation
If you use our work, please consider citing:
```bibtex
@article{koleilat2024biomedcoop,
        title={BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models},
        author={Koleilat, Taha and Asgariandehkordi, Hojat and Rivaz, Hassan and Xiao, Yiming},
        journal={arXiv preprint arXiv:2411.15232},
        year={2024}
}
```