Abstract
In pseudo-labeling (PL), which is a type of semi-supervised learning, pseudo-labels are assigned based on the confidence scores provided by the classifier; therefore, accurate confidence is important for successful PL. In this study, we propose a PL algorithm based on an energy-based model (EBM), which is referred to as the energy-based PL (EBPL). In EBPL, a neural network-based classifier and an EBM are jointly trained by sharing their feature extraction parts. This approach enables the model to learn both the class decision boundary and input data distribution, enhancing confidence calibration during network training. The experimental results demonstrate that EBPL outperforms the existing PL method in semi-supervised image classification tasks, with superior confidence calibration error and recognition accuracy.
Abstract (translated)
在伪标签（PL）中，这是一种半监督学习方法，伪标签根据分类器的置信分数分配；因此，准确的置信度对于成功的PL至关重要。在这项研究中，我们提出了一个基于能量模型的PL算法，被称为能量为基础的PL（EBPL）。在EBPL中，一个基于神经网络的分类器和一个基于能量模型的分类器共享其特征提取部分进行共同训练。这种方法使得模型能够在网络训练过程中同时学习分类决策边界和输入数据分布，从而提高信心估计误差和识别准确性。实验结果表明，EBPL在半监督图像分类任务中优于现有PL方法，具有卓越的置信度估计误差和识别准确性。
URL
https://arxiv.org/abs/2404.09585
