Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in the pseudo supervision. In this work, we propose robust mutual learning that improves the prior approach in two aspects. First, the vanilla mutual learners suffer from the coupling issue that models may converge to learn homogeneous knowledge. We resolve this issue by introducing mean teachers to generate mutual supervisions so that there is no direct interaction between the two students. We also show that strong data augmentations, model noises and heterogeneous network architectures are essential to alleviate the model coupling. Second, we notice that mutual learning fails to leverage the network's own ability for pseudo label refinement. Therefore, we introduce self-rectification that leverages the internal knowledge and explicitly rectifies the pseudo labels before the mutual teaching. Such self-rectification and mutual teaching collaboratively improve the pseudo label accuracy throughout the learning. The proposed robust mutual learning demonstrates state-of-the-art performance on semantic segmentation in low-data regime.

翻译：最近的半监督学习方法通常以假标签为基础。 由于 SSL 的性能受到伪标签质量的极大影响,我们建议相互学习以有效抑制伪标签监管中的噪音。 在这项工作中,我们建议相互学习,在两个方面改进先前的方法。 首先,香草相互学习者受到混合问题的影响,模型可以聚集在一起学习同质知识。我们通过引入低级教师来解决这一问题,从而产生相互监督,从而避免两个学生之间的直接互动。我们还表明,强大的数据增强、模型噪音和混杂的网络结构对于缓解模型组合至关重要。 其次,我们注意到,相互学习未能利用网络本身的能力来改进伪标签。因此,我们引入自我强化,利用内部知识,并在相互教学之前明确校正假标签。这种自我恢复和相互教学可以提高整个学习过程中的假标签准确性。 拟议的强有力相互学习显示低数据系统中的语义分割状态。