Meta-Learning for Semi-Supervised Few-Shot Classification

by   Mengye Ren, et al.
Princeton University

In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different classification problems, each with a small labeled training set and its corresponding test set. In this work, we advance this few-shot classification paradigm towards a scenario where unlabeled examples are also available within each episode. We consider two situations: one where all unlabeled examples are assumed to belong to the same set of classes as the labeled examples of the episode, as well as the more challenging situation where examples from other distractor classes are also provided. To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes. These models are trained in an end-to-end way on episodes, to learn to leverage the unlabeled examples successfully. We evaluate these methods on versions of the Omniglot and miniImageNet benchmarks, adapted to this new framework augmented with unlabeled examples. We also propose a new split of ImageNet, consisting of a large set of classes, with a hierarchical structure. Our experiments confirm that our Prototypical Networks can learn to improve their predictions due to unlabeled examples, much like a semi-supervised algorithm would.


page 4

page 10

page 15


Learning to Self-Train for Semi-Supervised Few-Shot Classification

Few-shot classification (FSC) is challenging due to the scarcity of labe...

Training few-shot classification via the perspective of minibatch and pretraining

Few-shot classification is a challenging task which aims to formulate th...

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

Few-shot classification (FSC) requires training models using a few (typi...

Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models

In this paper, we propose a deep invertible hybrid model which integrate...

Semi-Supervised Few-Shot Learning with Local and Global Consistency

Learning from a few examples is a key characteristic of human intelligen...

Confusable Learning for Large-class Few-Shot Classification

Few-shot image classification is challenging due to the lack of ample sa...

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

Few-shot classification refers to learning a classifier for new classes ...

Please sign up or login with your details

Forgot password? Click here to reset