Deep semi-supervised learning is a fast-growing field with a range of practical applications. This paper provides a comprehensive survey on both fundamentals and recent advances in deep semi-supervised learning methods from model design perspectives and unsupervised loss functions. We first present a taxonomy for deep semi-supervised learning that categorizes existing methods, including deep generative methods, consistency regularization methods, graph-based methods, pseudo-labeling methods, and hybrid methods. Then we offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences. In addition to the past few years' progress, we further discuss some shortcomings of existing methods and provide some tentative heuristic solutions for solving these open problems.

本文针对深度半监督学习方法中的模型设计和无监督损失函数的透视，提供了关于基础和最新进展的全面调查，首先提出了将现有方法分类的深度半监督学习分类法，包括深度生成方法、一致性正则化方法、基于图的方法、伪标记方法和混合方法，然后全面回顾了52种代表性方法，并详细比较了这些方法在损失类型、贡献和架构差异方面的差异。除了过去几年的进展外，我们进一步讨论了一些现有方法的缺点，并提供了一些试探性的启发式解决方案来解决这些开放性问题。

深度半监督学习调研