Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios. However, if data in additional modalities exist (e.g. text) this can compensate for the lack of data and improve the classification results. To overcome this data scarcity, we design a cross-modal feature generation framework capable of enriching the low populated embedding space in few-shot scenarios, leveraging data from the auxiliary modality. Specifically, we train a generative model that maps text data into the visual feature space to obtain more reliable prototypes. This allows to exploit data from additional modalities (e.g. text) during training while the ultimate task at test time remains classification with exclusively visual data. We show that in such cases nearest neighbor classification is a viable approach and outperform state-of-the-art single-modal and multimodal few-shot learning methods on the CUB-200 and Oxford-102 datasets.
@article{arxiv.2011.08899,
title = {Multimodal Prototypical Networks for Few-shot Learning},
author = {Frederik Pahde and Mihai Puscas and Tassilo Klein and Moin Nabi},
journal= {arXiv preprint arXiv:2011.08899},
year = {2020}
}