Chaoyi Li, Meng Li, Can Peng, Brian C. Lovell, "Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification", MICCAI 2023 [paper]

In this repository, we provide the demo of DCLU to reproduce the experiments on CIFAR10 in the supplementary material.

pip install -r requirements.txt

“*” denotes results reported by Kong, Y., Liu, L., Wang, J., & Tao, D. (2021). Adaptive curriculum learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 5067-5076).

Cite as below if you find this repository is helpful to your project.

@inproceedings{li2023dynamic,
  title={Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification},
  author={Li, Chaoyi and Li, Meng and Peng, Can and Lovell, Brian C},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={747--757},
  year={2023},
  organization={Springer}
}

• Many thanks to the amazing work Evidential Deep Learning to Quantify Classification Uncertainty