Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging
即兴、适应、克服——用于医疗影像中视觉语言模型高效微调的望远镜适配器
机构 * Centre for Artificial Intelligence and Robotics, Indian Institute of Technology Mandi(印度理工学院曼迪分校人工智能与机器人中心)
AI总结 本文提出望远镜适配器,通过深度感知缩放提升视觉语言分割模型在医疗影像中的微调效率,仅用613k参数在五个数据集上取得优异性能。
Comments Accepted at the IEEE/CVF winter conference on applications of computer vision (WACV 2026)