Co-training, extended from self-training, is one of the frameworks for semi-supervised learning. Without natural split of features, single-view co-training works at the cost of training extra classifiers, where the algorithm should be delicately designed to prevent individual classifiers from collapsing into each other. To remove these obstacles which deter the adoption of single-view co-training, we present a simple and efficient algorithm Multi-Head Co-Training. By integrating base learners into a multi-head structure, the model is in a minimal amount of extra parameters. Every classification head in the unified model interacts with its peers through a "Weak and Strong Augmentation" strategy, in which the diversity is naturally brought by the strong data augmentation. Therefore, the proposed method facilitates single-view co-training by 1). promoting diversity implicitly and 2). only requiring a small extra computational overhead. The effectiveness of Multi-Head Co-Training is demonstrated in an empirical study on standard semi-supervised learning benchmarks.

翻译：协同训练是自训练的一种扩展，是半监督学习的框架之一。在缺乏自然特征划分的情况下，单视图协同训练以训练额外分类器为代价运行，其算法需要精心设计以防止各分类器相互坍缩。为消除阻碍单视图协同训练应用的障碍，本文提出一种简洁高效的多头协同训练算法。通过将基学习器集成到多头结构中，该模型仅需极少量的额外参数。统一模型中的每个分类头通过“弱增强与强增强”策略与其对应模块交互，其中强数据增强自然引入了多样性。因此，所提方法通过以下两方面促进了单视图协同训练：1）隐式提升多样性；2）仅需少量额外计算开销。在标准半监督学习基准上的实证研究验证了多头协同训练的有效性。