Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some confidence-related regularizers cannot comprehensively catch the uncertainty. Therefore, we propose a new self-training framework to combine uncertainty information of both model and dataset. Specifically, we propose to use Expectation-Maximization (EM) to smooth the labels and comprehensively estimate the uncertainty information. We further design a basis extraction network to estimate the initial basis from the dataset. The obtained basis with uncertainty can be filtered based on uncertainty information. It can then be transformed into the real hard label to iteratively update the model and basis in the retraining process. Experiments on image classification and semantic segmentation show the advantages of our methods among confidence-aware self-training algorithms with 1-3 percentage improvement on different datasets.

翻译：自训练是深度学习中的一种强大方法，其关键过程在于寻找用于建模的伪标签。然而，先前的自训练算法因硬标签带来的过度自信问题而表现不佳，即使某些与置信度相关的正则化器也无法全面捕捉不确定性。为此，我们提出了一种新的自训练框架，将模型和数据集的不确定性信息相结合。具体而言，我们利用期望最大化（EM）来平滑标签，并全面估计不确定性信息。我们还设计了一个基提取网络，用于从数据集中估计初始基。基于不确定性信息，所获得带有不确定性的基可以被过滤，随后在重新训练过程中转换为真实的硬标签，以迭代更新模型和基。在图像分类和语义分割任务上的实验表明，我们的方法在置信度感知的自训练算法中具有优势，在不同数据集上实现了1-3个百分点的性能提升。