@inproceedings{Anon2025MedFastsamImprovingTransferEfficiency,
  title = {Med-FastSAM: Improving Transfer Efficiency of SAM to Domain-Generalised Medical Image Segmentation},
  year = {2025},
  url = {https://repository.lincoln.ac.uk/articles/conference_contribution/Med-FastSAM_Improving_Transfer_Efficiency_of_SAM_to_Domain-Generalised_Medical_Image_Segmentation/28053113},
  urldate = {2025-09-12},
  abstract = {Medical image segmentation is a crucial computer vision task in medical image analysis. Recently, the Segment Anything Model (SAM) has made significant advancements in natural image segmentation. Despite current studies indicating the potential of SAM to revolutionise medical image segmentation using parameter- efficient fine-tuning techniques, it still faces three primary challenges. Firstly, these methods still rely on the large vision transformer of SAM, which is computationally expensive. Secondly, the point and box prompt modes of SAM demand manual annotations, which are time-consuming and expensive in medical sce- narios and reduce their clinical applicability. Thirdly, SAM leverages large-size patches to predict masks, resulting in the loss of fine-grained details. To address these limitations, in this paper, we propose a fast-transferring architecture for adapting SAM to domain-g},
  keywords = {I400 - Artificial intelligence, I440 - Computer vision, I460 - Machine learning, I500 - Health informatics},
  note = {Metadata from repository RSS; authors/venue not verified.},
}

{"_id":"fFdM6aTt7BqhZZAG4","bibbaseid":"anonymous-medfastsamimprovingtransferefficiencyofsamtodomaingeneralisedmedicalimagesegmentation-2025","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Med-FastSAM: Improving Transfer Efficiency of SAM to Domain-Generalised Medical Image Segmentation","year":"2025","url":"https://repository.lincoln.ac.uk/articles/conference_contribution/Med-FastSAM_Improving_Transfer_Efficiency_of_SAM_to_Domain-Generalised_Medical_Image_Segmentation/28053113","urldate":"2025-09-12","abstract":"Medical image segmentation is a crucial computer vision task in medical image analysis. Recently, the Segment Anything Model (SAM) has made significant advancements in natural image segmentation. Despite current studies indicating the potential of SAM to revolutionise medical image segmentation using parameter- efficient fine-tuning techniques, it still faces three primary challenges. Firstly, these methods still rely on the large vision transformer of SAM, which is computationally expensive. Secondly, the point and box prompt modes of SAM demand manual annotations, which are time-consuming and expensive in medical sce- narios and reduce their clinical applicability. Thirdly, SAM leverages large-size patches to predict masks, resulting in the loss of fine-grained details. To address these limitations, in this paper, we propose a fast-transferring architecture for adapting SAM to domain-g","keywords":"I400 - Artificial intelligence, I440 - Computer vision, I460 - Machine learning, I500 - Health informatics","note":"Metadata from repository RSS; authors/venue not verified.","bibtex":"@inproceedings{Anon2025MedFastsamImprovingTransferEfficiency,\n title = {Med-FastSAM: Improving Transfer Efficiency of SAM to Domain-Generalised Medical Image Segmentation},\n year = {2025},\n url = {https://repository.lincoln.ac.uk/articles/conference_contribution/Med-FastSAM_Improving_Transfer_Efficiency_of_SAM_to_Domain-Generalised_Medical_Image_Segmentation/28053113},\n urldate = {2025-09-12},\n abstract = {Medical image segmentation is a crucial computer vision task in medical image analysis. Recently, the Segment Anything Model (SAM) has made significant advancements in natural image segmentation. Despite current studies indicating the potential of SAM to revolutionise medical image segmentation using parameter- efficient fine-tuning techniques, it still faces three primary challenges. Firstly, these methods still rely on the large vision transformer of SAM, which is computationally expensive. Secondly, the point and box prompt modes of SAM demand manual annotations, which are time-consuming and expensive in medical sce- narios and reduce their clinical applicability. Thirdly, SAM leverages large-size patches to predict masks, resulting in the loss of fine-grained details. To address these limitations, in this paper, we propose a fast-transferring architecture for adapting SAM to domain-g},\n keywords = {I400 - Artificial intelligence, I440 - Computer vision, I460 - Machine learning, I500 - Health informatics},\n note = {Metadata from repository RSS; authors/venue not verified.},\n}\n","key":"Anon2025MedFastsamImprovingTransferEfficiency","id":"Anon2025MedFastsamImprovingTransferEfficiency","bibbaseid":"anonymous-medfastsamimprovingtransferefficiencyofsamtodomaingeneralisedmedicalimagesegmentation-2025","role":"","urls":{"Paper":"https://repository.lincoln.ac.uk/articles/conference_contribution/Med-FastSAM_Improving_Transfer_Efficiency_of_SAM_to_Domain-Generalised_Medical_Image_Segmentation/28053113"},"keyword":["I400 - Artificial intelligence","I440 - Computer vision","I460 - Machine learning","I500 - Health informatics"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/dntGg3DM344pSSuT5","dataSources":["2HfsfKMbpJmabYHxY"],"keywords":["i400 - artificial intelligence","i440 - computer vision","i460 - machine learning","i500 - health informatics"],"search_terms":["med","fastsam","improving","transfer","efficiency","sam","domain","generalised","medical","image","segmentation"],"title":"Med-FastSAM: Improving Transfer Efficiency of SAM to Domain-Generalised Medical Image Segmentation","year":2025}