Learning a Universal Template for Few-shot Dataset Generalization

by   Eleni Triantafillou, et al.

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from new datasets using only a few examples. To this end, we propose to utilize the diverse training set to construct a universal template: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.


page 1

page 2

page 3

page 4


Gradient-Based Meta-Learning Using Uncertainty to Weigh Loss for Few-Shot Learning

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-l...

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

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

A Universal Representation Transformer Layer for Few-Shot Image Classification

Few-shot classification aims to recognize unseen classes when presented ...

Selecting Relevant Features from a Universal Representation for Few-shot Classification

Popular approaches for few-shot classification consist of first learning...

How to Train Your MAML to Excel in Few-Shot Classification

Model-agnostic meta-learning (MAML) is arguably the most popular meta-le...

One-shot Key Information Extraction from Document with Deep Partial Graph Matching

Automating the Key Information Extraction (KIE) from documents improves ...

Structurally Diverse Sampling Reduces Spurious Correlations in Semantic Parsing Datasets

A rapidly growing body of research has demonstrated the inability of NLP...