English

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

Computer Vision and Pattern Recognition 2023-05-29 v3

Abstract

Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus, degenerating to the self-training ones, and produce low-confidence pseudo labels from the perturbed inputs during training. To address these issues, we propose an Uncertainty-guided Collaborative Mean-Teacher (UCMT) for semi-supervised semantic segmentation with the high-confidence pseudo labels. Concretely, UCMT consists of two main components: 1) collaborative mean-teacher (CMT) for encouraging model disagreement and performing co-training between the sub-networks, and 2) uncertainty-guided region mix (UMIX) for manipulating the input images according to the uncertainty maps of CMT and facilitating CMT to produce high-confidence pseudo labels. Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation. Extensive experiments on four public medical image datasets including 2D and 3D modalities demonstrate the superiority of UCMT over the state-of-the-art. Code is available at: https://github.com/Senyh/UCMT.

Keywords

Cite

@article{arxiv.2301.04465,
  title  = {Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation},
  author = {Zhiqiang Shen and Peng Cao and Hua Yang and Xiaoli Liu and Jinzhu Yang and Osmar R. Zaiane},
  journal= {arXiv preprint arXiv:2301.04465},
  year   = {2023}
}
R2 v1 2026-06-28T08:09:19.372Z