Semi-supervised learning (SSL) methods, which can leverage a large amount of
unlabeled data for improved performance, has attracted increasing attention
recently. In this paper, we introduce a novel Context-aware Conditional Cross
Pseudo Supervision method (referred as C$^3$PS) for semi-supervised medical
image segmentation. Unlike previously published Cross Pseudo Supervision (CPS)
works, this paper introduces a novel Conditional Cross Pseudo Supervision
(CCPS) mechanism where the cross pseudo supervision is conditioned on a given
class label. Context-awareness is further introduced in the CCPS to improve the
quality of pseudo-labels for cross pseudo supervision. The proposed method has
the additional advantage that in the later training stage, it can focus on the
learning of hard organs. Validated on two typical yet challenging medical image
segmentation tasks, our method demonstrates superior performance over the
state-of-the-art methods.

提出了一种新的 Context-aware Conditional Cross Pseudo Supervision，可用于半监督医学图像分割，具有条件的跨伪监督机制和上下文感知，能够在后期训练阶段集中学习难分割的器官，并在挑战性的医学图像分割任务中超过现有的方法。