This is the project of WSRDP You can cite this paper in:
@article{yan2022lightweight, title={A lightweight weakly supervised learning segmentation algorithm for imbalanced image based on rotation density peaks}, author={Yan, Ming and Chen, Yewang and Chen, Yi and Zeng, Guoyao and Hu, Xiaoliang and Du, Jixiang}, journal={Knowledge-Based Systems}, volume={244}, pages={108513}, year={2022}, publisher={Elsevier} }
The main body of the code is divided into three parts: the training part of SVM and SVR, and the main program part of RDP. If you want to use the parameters in the paper directly, you can run the code in the third part directly.
Most of the test sets that need to segment small objects can use the weak parameters trained in the paper. Some special parameters are documented in WSRDP_example.pdf.