Text-driven adaptation of foundation models for few-shot surgical workflow analysis
We propose a text-driven adaptation approach that mitigates the modality gap and handles multiple downstream tasks in surgical workflow analysis, with minimal reliance on large annotated datasets. The code and dataset will be released in https://github.com/CAMMApublic/Surg-FTDA .
Authors
- T. Chen
- Nassir Navab (ORCID: https://orcid.org/0000-0002-6032-5611)
- Vinkle Srivastav (ORCID: https://orcid.org/0000-0002-1044-038X)
- Nicolas Padoy (ORCID: https://orcid.org/0000-0002-5010-4137)
- Kun Yuan (ORCID: https://orcid.org/0000-0002-3681-2196)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Institut de Chirurgie Guidée par l'Image (FR)
- Technical University of Munich (DE)
- Université de Strasbourg (FR)
Publication Details
- Journal
- International Journal of Computer Assisted Radiology and Surgery
- Published
- 2025-04-17
- DOI
- https://doi.org/10.1007/s11548-025-03341-0
- Citations
- 4
- Primary Topic
- Surgical Simulation and Training
- Type
- article
- Field-Weighted Citation Impact
- 8.03
Funders
- Equipex
- European Commission
- Agence Nationale de la Recherche
- Université de Strasbourg
- Grand Équipement National De Calcul Intensif
- European Research Council