myeongkyunkang
/

siglip2-so400m-patch16-512-lofi-medg

Image Feature Extraction

zero-shot-image-classification

Model card Files Files and versions

LoFi-MedG

Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models

This repository contains the model described in Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models.

For more details, please refer to the code.

Downloads last month: 35

Safetensors

Model size

1B params

Tensor type

F32

·

Inference Providers NEW

Image Feature Extraction

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for myeongkyunkang/siglip2-so400m-patch16-512-lofi-medg

Base model

google/siglip2-so400m-patch16-512

Finetuned

(5)

this model

Space using myeongkyunkang/siglip2-so400m-patch16-512-lofi-medg 1

Paper for myeongkyunkang/siglip2-so400m-patch16-512-lofi-medg

Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models

Paper • 2608.00976 • Published Aug 2