Cross-Modulation Networks for Few-Shot Learning

TL;DR

Cross-Modulation Networks enable support and query examples to interact at multiple levels during feature extraction, improving few-shot learning performance by integrating information throughout the process.

Contribution

This paper introduces Cross-Modulation Networks that facilitate multi-level interaction between support and query examples in few-shot learning, enhancing existing embedding-based methods.

Findings

Improved performance on miniImageNet 5-way 1-shot task.

Close to state-of-the-art results with initial experiments.

Demonstrated benefits of multi-level information integration.

Abstract

A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and query examples at a very late stage of the prediction pipeline. Inspired by this observation, we hypothesize that there may be benefits to combining the information at various levels of abstraction along the pipeline. We present an architecture called Cross-Modulation Networks which allows support and query examples to interact throughout the feature extraction process via a feature-wise modulation mechanism. We adapt the Matching Networks architecture to take advantage of these interactions and show encouraging initial results on miniImageNet in the 5-way, 1-shot setting, where we close the gap with state-of-the-art.