On the Pitfalls of Entropy-Based Uncertainty for Multi-class Semi-supervised Segmentation

Martin Van Waerebeke, Gregory A. Lodygensky, Jose Dolz. On the Pitfalls of Entropy-Based Uncertainty for Multi-class Semi-supervised Segmentation. In Carole H. Sudre, Christian F. Baumgartner, Adrian V. Dalca, Chen Qin, Ryutaro Tanno, Koen Van Leemput, William M. Wells III, editors, Uncertainty for Safe Utilization of Machine Learning in Medical Imaging - 4th International Workshop, UNSURE 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings. Volume 13563 of Lecture Notes in Computer Science, pages 36-46, Springer, 2022. [doi]

@inproceedings{WaerebekeLD22,
  title = {On the Pitfalls of Entropy-Based Uncertainty for Multi-class Semi-supervised Segmentation},
  author = {Martin Van Waerebeke and Gregory A. Lodygensky and Jose Dolz},
  year = {2022},
  doi = {10.1007/978-3-031-16749-2_4},
  url = {https://doi.org/10.1007/978-3-031-16749-2_4},
  researchr = {https://researchr.org/publication/WaerebekeLD22},
  cites = {0},
  citedby = {0},
  pages = {36-46},
  booktitle = {Uncertainty for Safe Utilization of Machine Learning in Medical Imaging - 4th International Workshop, UNSURE 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings},
  editor = {Carole H. Sudre and Christian F. Baumgartner and Adrian V. Dalca and Chen Qin and Ryutaro Tanno and Koen Van Leemput and William M. Wells III},
  volume = {13563},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-031-16749-2},
}