Revisiting Semi-Supervised Learning in the Era of Foundation Models
complementary pseudo-labelseffective baselineensemble pseudo-labelingfine-tuning techniquesmodel performanceparameter-efficient fine-tuningpseudo-labelsrobust learningscalable learningsemi-supervised learningsupervisory signalssystematic studytraditional ssl methodsunlabeled datavfm backbonesvision foundation models
Semi-supervised learning (SSL) enhances model performance by leveraging abundant unlabeled data alongside limited labeled data. As vision foundation models (VFMs) become central to modern vision applications, this paper revisits SSL in the context of these powerful pre-trained models. We conduct a systematic study on tasks where frozen VFMs underperform and reveal several key insights when fine-tuning them. First, parameter-efficient fine-tuning (PEFT) using only labeled data often surpasses traditional SSL methods