Semi-supervised learning (SSL) has witnessed remarkable progress, resulting
in the emergence of numerous method variations. However, practitioners often
encounter challenges when attempting to deploy these methods due to their
subpar performance. In this paper, we present a novel SSL approach named
FineSSL that significantly addresses this limitation by adapting pre-trained
foundation models. We identify the aggregated biases and cognitive deviation
problems inherent in foundation models, and propose a simple yet effective
solution by imposing balanced margin softmax and decoupled label smoothing.
Through extensive experiments, we demonstrate that FineSSL sets a new state of
the art for SSL on multiple benchmark datasets, reduces the training cost by
over six times, and can seamlessly integrate various fine-tuning and modern SSL
algorithms. The source code is available at
this https URL

通过在预训练基础模型中应用平衡的边界 Softmax 和解耦式标签平滑，FineSSL 提供了一种新的半监督学习方法，显著改善了现有方法的性能问题，并在多个基准数据集上达到了新的最先进水平，降低了训练成本超过六倍，可以无缝集成各种微调和现代半监督学习算法。