Knowledge-Mining-from-Large-Models

This repository provides the open-source code for the paper "Semi-Supervised Medical Image Segmentation via Knowledge Mining from Large Models." It includes the complete implementation necessary to replicate the results presented in the study.

How to Run the Code

1. Clone the Repository:

   git clone <repository-url>

2. Prepare the Data: Unzip the data/Kvasir-SEG.zip file to extract the dataset.

3. Run the Code:

   • Navigate to the Jupyter notebook src/Unet-Kvasir-SEG.ipynb for the main implementation of our method.
   • This notebook includes code for both the proposed method and baseline methods, which utilize point and bounding box prompts with a 50% train split.

Feel free to explore and modify the code as needed for your research and development.