Few-shot learning
Machine learning paradigm using minimal training data
From Wikipedia, the free encyclopedia
Few-shot learning (FSL) is a problem setup in machine learning in which a model learns to perform a task, typically classification, from only a small number of labeled examples per class, rather than the large datasets required by conventional supervised learning.[1][2][3][4]
One-shot learning is the special case of the N-way K-shot framing in which K equals one, such that the model must generalize from exactly one example per class.[1][5][6][7]
The limiting case of few-shot learning is zero-shot learning that requires no training on examples of the class to be classified; instead, the classification task must be generalized from examples of other classes.[6][8][9]
