Prototypical Networks for Few-shot Learning

Code

• github.com/jakesnell/prototypical-networks
  Officialpytorch★ 1,223
• github.com/learnables/learn2learn
  pytorch★ 2,878
• github.com/sicara/easy-few-shot-learning
  pytorch★ 1,301
• github.com/cnguyen10/few_shot_meta_learning
  pytorch★ 257
• github.com/amazon-research/dse
  pytorch★ 43
• github.com/RongKaiWeskerMA/INSTA
  pytorch★ 13
• github.com/jsalbert/prototypical-networks
  pytorch★ 8
• github.com/msfuxian/DualAttentionNet
  mindspore★ 6
• github.com/ajfisch/few-shot-cp
  pytorch★ 6
• github.com/andrewbo29/mtm-meta-learning-sa
  pytorch★ 3

Abstract

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. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

Tasks

Benchmark Results

Reproductions