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 RESULT LEADERBOARD
Few-Shot Image Classification CUB 200 50-way (0-shot) Prototypical Networks Accuracy 54.6 # 1
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Prototypical Networks Accuracy 49.42 # 40
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Prototypical Networks Accuracy 68.20 # 31
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Prototypical Networks Accuracy 96% # 11
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Prototypical Networks Accuracy 98.8 # 8
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Prototypical Networks Accuracy 98.9% # 9
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Prototypical Networks Accuracy 99.7 # 7

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Few-Shot Image Classification Mini-Imagenet 5-way (10-shot) Prototypical Networks Accuracy 74.3 # 5
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) ProtoNet (Snell et al., 2017) Accuracy 45.31 # 4
Few-Shot Image Classification Stanford Cars 5-way (1-shot) Prototypical Nets++ Accuracy 40.90 # 3
Few-Shot Image Classification Stanford Cars 5-way (5-shot) Prototypical Nets++ Accuracy 52.93 # 3
Few-Shot Image Classification Stanford Dogs 5-way (5-shot) Prototypical Nets++ Accuracy 48.19 # 3
Image Classification Tiered ImageNet 5-way (5-shot) Prototypical Net Accuracy 69.57 # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet