Pseudo-label Learning with Calibrated Confidence Using an Energy-based Model

arXiv:2404.09585v1 Announce Type: new
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 …

abstract algorithm arxiv classifier confidence cs.cv energy labeling labels semi-supervised semi-supervised learning study supervised learning type