Timezone: »

Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou · Hugo Larochelle · Richard Zemel · Vincent Dumoulin

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @ Virtual

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 \emph{new datasets} using only a few examples. To this end, we propose to utilize the diverse training set to construct a \emph{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.

Author Information

Eleni Triantafillou (University of Toronto, Vector Institute)
Hugo Larochelle (Google Brain)
Richard Zemel (Vector Institute)
Vincent Dumoulin (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors