| ---
|
| license: mit
|
| ---
|
| ## Third-party Baselines Used in the Demo
|
|
|
| The accompanying CapCLIP Hugging Face Space includes the following third-party baseline models for comparison:
|
|
|
| | Model | Source / Authors | Use in Demo |
|
| |---|---|---|
|
| | MedCLIP | Wang et al., EMNLP 2022 | Medical vision-language baseline |
|
| | BioMedCLIP | Microsoft Research | Biomedical vision-language baseline |
|
| | MedImageInsight | Codella et al. / public Hugging Face implementation | General medical imaging embedding baseline |
|
| | OpenAI CLIP | OpenAI | General-domain CLIP baseline |
|
|
|
| These models are not proposed as part of CapCLIP. They are included to allow transparent comparison with general-domain, biomedical, and medical imaging foundation models. We acknowledge and thank the original authors and organisations for releasing their code and/or model weights.
|
|
|
| Users should consult the original model cards, repositories, licences, and intended-use statements before reusing any third-party baseline model outside this research demo. |
