Prototypical Networks for Few-shot Learning
Prototypical Networks for Few-shot Learning
复制标题
DOI：
--
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Jake Snell;Kevin Swersky;R. Zemel
中科院分区：
文献类型：
--
作者：
Jake Snell;Kevin Swersky;R. Zemel
我们提出了原型网络的问题，少数镜头分类，其中分类器必须推广到新的类中没有看到的训练集，只有少量的例子，每个新的类。原型网络学习一个度量空间，在这个度量空间中，可以通过计算到每个类的原型表示的距离来执行分类。与最近的几次学习方法相比，它们反映了一种更简单的归纳偏差，这在这种有限的数据制度中是有益的，并取得了优异的结果。我们提供的分析表明，一些简单的设计决策可以产生实质性的改进，最近的方法，涉及复杂的架构选择和元学习。我们进一步将原型网络扩展到零射击学习，并在CU-Birds数据集上实现了最先进的结果。
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.