Local Propagation for Few-Shot Learning

TL;DR

This paper introduces local propagation, a method that combines local image features and transductive inference to improve few-shot learning accuracy across different data availability scenarios.

Contribution

It proposes a novel local propagation technique that unifies local feature use and transductive inference for robust few-shot learning.

Findings

Improves accuracy over existing methods in few-shot tasks.

Provides a universally safe inference approach for various data settings.

Leverages local features and graph-based label propagation.

Abstract

The challenge in few-shot learning is that available data is not enough to capture the underlying distribution. To mitigate this, two emerging directions are (a) using local image representations, essentially multiplying the amount of data by a constant factor, and (b) using more unlabeled data, for instance by transductive inference, jointly on a number of queries. In this work, we bring these two ideas together, introducing \emph{local propagation}. We treat local image features as independent examples, we build a graph on them and we use it to propagate both the features themselves and the labels, known and unknown. Interestingly, since there is a number of features per image, even a single query gives rise to transductive inference. As a result, we provide a universally safe choice for few-shot inference under both non-transductive and transductive settings, improving accuracy over corresponding methods. This is in contrast to existing solutions, where one needs to choose the method depending on the quantity of available data.