Method evidence record
Online Few-shot Learning
Online Few-shot Learning combines the streaming update principle of online learning with the data-efficiency goal of few-shot learning, enabling a model to continuously adapt to new tasks or classes from only a handful of labeled examples as data arrives sequentially — without access to the full historical dataset.
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
Online Few-shot Learning (Streaming Meta-Learning from Scarce Labels)
Taxonomic method record · ml-model / machine-learning
- Finn, C., Rajeswaran, A., Kakade, S., & Levine, S. (2019). Online Meta-Learning. Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, 1920–1930. · URL
- Javed, K., & White, M. (2019). Meta-Learning Representations for Continual Learning. Advances in Neural Information Processing Systems (NeurIPS), 32. · URL
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
No curated claims yet
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.