Timezone: »

The Role of Global Labels in Few-Shot Classification and How to Infer Them
Ruohan Wang · Massimiliano Pontil · Carlo Ciliberto

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @

Few-shot learning is a central problem in meta-learning, where learners must quickly adapt to new tasks given limited training data. Recently, feature pre-training has become a ubiquitous component in state-of-the-art meta-learning methods and is shown to provide significant performance improvement. However, there is limited theoretical understanding of the connection between pre-training and meta-learning. Further, pre-training requires global labels shared across tasks, which may be unavailable in practice. In this paper, we show why exploiting pre-training is theoretically advantageous for meta-learning, and in particular the critical role of global labels. This motivates us to propose Meta Label Learning (MeLa), a novel meta-learning framework that automatically infers global labels to obtains robust few-shot models. Empirically, we demonstrate that MeLa is competitive with existing methods and provide extensive ablation experiments to highlight its key properties.

Author Information

Ruohan Wang (Institute for Infocomm Research)
Massimiliano Pontil (IIT & UCL)
Carlo Ciliberto (University College London)

More from the Same Authors