Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples. In this work, we propose a new strategy based on feature selection, which is both simpler and more effective than previous feature adaptation approaches. First, we obtain a multi-domain representation by training a set of semantically different feature extractors. Then, given a few-shot learning task, we use our multi-domain feature bank to automatically select the most relevant representations. We show that a simple non-parametric classifier built on top of such features produces high accuracy and generalizes to domains never seen during training, which leads to state-of-the-art results on MetaDataset and improved accuracy on mini-ImageNet.
@article{arxiv.2003.09338,
title = {Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification},
author = {Nikita Dvornik and Cordelia Schmid and Julien Mairal},
journal= {arXiv preprint arXiv:2003.09338},
year = {2020}
}