Prototypical Networks for Few-shot Learning

NeurIPS 2017 Jake SnellKevin SwerskyRichard S. Zemel

We propose 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. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Few-Shot Image Classification CUB-200 - 0-Shot Learning Prototypical-Nets Accuracy 54.6% # 1
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning Prototypical-Nets + C64F feature extractor Accuracy 49.42% # 23
Few-Shot Image Classification Mini-ImageNet - 5-Shot Learning Prototypical-Nets + C64F feature extractor Accuracy 68.20% # 17
Few-Shot Image Classification OMNIGLOT - 1-Shot Learning Prototypical-Nets Accuracy 98.8% # 3
Few-Shot Image Classification OMNIGLOT - 5-Shot Learning Prototypical-Nets Accuracy 99.7% # 3