Recent breakthroughs in the field of semi-supervised learning have achieved results that match state-of-the-art traditional supervised learning methods. Most successful semi-supervised learning approaches in computer vision focus on leveraging huge amount of unlabeled data, learning the general representation via data augmentation and transformation, creating pseudo labels, implementing different loss functions, and eventually transferring this knowledge to more task-specific smaller models. In this paper, we aim to conduct our analyses on three different aspects of SimCLR, the current state-of-the-art semi-supervised learning framework for computer vision. First, we analyze properties of contrast learning on fine-tuning, as we understand that contrast learning is what makes this method so successful. Second, we research knowledge distillation through teacher-forcing paradigm. We observe that when the teacher and the student share the same base model, knowledge distillation will achieve better result. Finally, we study how transfer learning works and its relationship with the number of classes on different data sets. Our results indicate that transfer learning performs better when number of classes are smaller.

翻译：在半监督的学习领域,最近的突破取得了与最先进的传统监督的学习方法相匹配的成果。在计算机视野中,大多数成功的半监督的学习方法侧重于利用大量未贴标签的数据,通过数据增强和转换学习一般代表,通过数据增强和转换学习一般代表,创建假标签,实施不同的损失功能,并最终将这种知识传授给更具体任务的小模型。在本文件中,我们的目标是对SimCLR的三个不同方面进行分析,即目前最先进的计算机视觉半监督的学习框架。首先,我们分析微调对比学习的特性,因为我们理解,对比学习是使这种方法如此成功的原因。第二,我们研究通过师范模式蒸馏知识。我们观察到,当教师和学生共享相同的基础模型时,知识蒸馏将取得更好的结果。最后,我们研究转移学习如何奏效,以及它与不同数据集的班级数量之间的关系。我们的结果显示,在班级数量小时,转移学习表现得更好。