Machine learningMachine learning

Semi-supervised Few-shot Learning

Semi-supervised Few-shot Learning (SS-FSL) trains models to classify new classes from only a handful of labeled examples per class, while simultaneously leveraging a pool of unlabeled data to enrich class representations. By combining meta-learning episodes with soft pseudo-label assignment for unlabeled samples, it achieves notably higher accuracy than purely supervised few-shot methods when abundant unlabeled data is available.

Open in MethodMindSoonVideoSoon

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Sources

  1. Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J. B., Larochelle, H., & Zemel, R. S. (2018). Meta-learning for semi-supervised few-shot classification. In International Conference on Learning Representations (ICLR 2018). link
  2. Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning (ICML 2017), PMLR 70, 1126–1135. link

Related methods

Referenced by

ScholarGateSemi-supervised Few-shot Learning (Semi-supervised Few-shot Learning (SS-FSL)). Retrieved 2026-06-04 from https://scholargate.app/en/machine-learning/semi-supervised-few-shot-learning