Prototypical Networks for Few-shot Learning

The paper proposes Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set given only a small number of examples of each new class. The networks learn a metric space in which classification is performed by computing distances to prototype representations of each class, reflecting a simpler inductive bias than recent few-shot learning approaches.

This simpler inductive bias proves beneficial in the limited-data regime, achieving excellent results, and the authors provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. Prototypical Networks are further extended to zero-shot learning, where they achieve state-of-the-art results on the CU-Birds dataset.