State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. An inherent drawback of this strategy stems from the quality of the uncertainty estimates, as pseudo-labels are filtered only based on their degree of uncertainty, regardless of the correctness of their predictions. Thus, assessing and enhancing the uncertainty of network predictions is of paramount importance in the pseudo-labeling process. In this work, we empirically demonstrate that SSL methods based on pseudo-labels are significantly miscalibrated, and formally demonstrate the minimization of the min-entropy, a lower bound of the Shannon entropy, as a potential cause for miscalibration. To alleviate this issue, we integrate a simple penalty term, which enforces the logit distances of the predictions on unlabeled samples to remain low, preventing the network predictions to become overconfident. Comprehensive experiments on a variety of SSL image classification benchmarks demonstrate that the proposed solution systematically improves the calibration performance of relevant SSL models, while also enhancing their discriminative power, being an appealing addition to tackle SSL tasks.

本文通过实证研究表明，基于伪标签的半监督学习方法存在显著的误校准问题。为了解决这个问题，本文提出了一个简单的惩罚项，通过保持未标记样本的预测结果的对数距离较小，防止网络预测过于自信。在多个半监督学习图像分类评估中，全面的实验结果表明，所提出的解决方案能够系统地提高相关模型的校准性能，并提升它们的区分力，是应对半监督学习任务的一个有吸引力的补充。

不要相信你所信任：半监督学习中的误校准