Semi-supervised learning (SSL) has been proven beneficial for mitigating the issue of limited labeled data especially on the task of volumetric medical image segmentation. Unlike previous SSL methods which focus on exploring highly confident pseudo-labels or developing consistency regularization schemes, our empirical findings suggest that inconsistent decoder features emerge naturally when two decoders strive to generate consistent predictions. Based on the observation, we first analyze the treasure of discrepancy in learning towards consistency, under both pseudo-labeling and consistency regularization settings, and subsequently propose a novel SSL method called LeFeD, which learns the feature-level discrepancy obtained from two decoders, by feeding the discrepancy as a feedback signal to the encoder. The core design of LeFeD is to enlarge the difference by training differentiated decoders, and then learn from the inconsistent information iteratively. We evaluate LeFeD against eight state-of-the-art (SOTA) methods on three public datasets. Experiments show LeFeD surpasses competitors without any bells and whistles such as uncertainty estimation and strong constraints, as well as setting a new state-of-the-art for semi-supervised medical image segmentation. Code is available at \textcolor{cyan}{https://github.com/maxwell0027/LeFeD}

翻译：半监督学习已被证明有助于缓解标注数据有限的问题，尤其是在体积医学图像分割任务中。与以往专注于挖掘高置信度伪标签或设计一致性正则化方案的半监督学习方法不同，我们的实证发现表明：当两个解码器致力于生成一致预测时，不一致的解码器特征会自然涌现。基于此观察，我们首先在伪标签和一致性正则化两种设置下，分析了在学习一致性过程中差异的价值，随后提出了一种名为LeFeD的新型半监督学习方法。该方法通过将两个解码器获得的特征级差异作为反馈信号输入编码器，从而学习这种差异。LeFeD的核心设计在于通过训练差异化解码器来扩大差异，并迭代性地从不一致信息中学习。我们在三个公开数据集上，将LeFeD与八种最先进方法进行了对比评估。实验表明，LeFeD无需借助不确定性估计或强约束等额外技巧即可超越竞争对手，并为半监督医学图像分割树立了新的标杆。代码开源于\textcolor{cyan}{https://github.com/maxwell0027/LeFeD}。