Can I read Federated Learning for 3D Segmentation on EtoBox?

Federated Learning for 3D Segmentation by xiaoyvonne8 is a document available to read on EtoBox.

What is Federated Learning for 3D Segmentation about?

The document presents FLAP-SAM, a federated learning approach that combines parameter-efficient fine-tuning techniques with the Segment Anything Model (SAM) for 3D medical image segmentation. By utilizing Low-Rank Adapters (LoRA) and selectively fine-tuning specific layers, the method significantly reduces communication costs while improving segmentation performance. Experimental results demonstrate a 48× reduction in communication costs and a 6% increase in Dice score compared to traditional fine-tuning me

Author

xiaoyvonne8

Language

EN