论文标题
ADT-SSL：半监督学习的自适应双阈值
ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learning
论文作者
论文摘要
半监督学习（SSL）通过输入标记和未标记的数据以共同训练模型来具有高级分类任务。但是，现有的SSL方法仅考虑其预测超出固定阈值（例如0.95）的未标记数据，而忽略了小于0.95的数据。我们认为这些废弃的数据比例很大，通常是硬样品，从而使模型培训受益。本文提出了一种自适应双阈值方法，用于半监督学习（ADT-SSL）。除固定阈值外，ADT还从标记的数据中提取了另一个类自适应阈值，以充分利用未标记的数据，其预测小于0.95，但比提取的数据大。因此，我们参与CE和$ L_2 $损失功能，分别从这两种类型的未标记数据中学习。对于高度相似的未标记数据，我们进一步设计了一种新颖的相似损失，以预测模型一致性。在包括CIFAR-10，CIFAR-100和SVHN在内的基准数据集上进行了广泛的实验。实验结果表明，拟议的ADT-SSL达到了最新的分类精度。
Semi-Supervised Learning (SSL) has advanced classification tasks by inputting both labeled and unlabeled data to train a model jointly. However, existing SSL methods only consider the unlabeled data whose predictions are beyond a fixed threshold (e.g., 0.95), ignoring the valuable information from those less than 0.95. We argue that these discarded data have a large proportion and are usually of hard samples, thereby benefiting the model training. This paper proposes an Adaptive Dual-Threshold method for Semi-Supervised Learning (ADT-SSL). Except for the fixed threshold, ADT extracts another class-adaptive threshold from the labeled data to take full advantage of the unlabeled data whose predictions are less than 0.95 but more than the extracted one. Accordingly, we engage CE and $L_2$ loss functions to learn from these two types of unlabeled data, respectively. For highly similar unlabeled data, we further design a novel similar loss to make the prediction of the model consistency. Extensive experiments are conducted on benchmark datasets, including CIFAR-10, CIFAR-100, and SVHN. Experimental results show that the proposed ADT-SSL achieves state-of-the-art classification accuracy.
