Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between multimodal representation learning and multiple instance learning. Based on this connection, we propose a generic framework for constructing permutation-invariant score functions with many existing multimodal representation learning approaches as special cases. Furthermore, we use the framework to derive a novel contrastive learning approach and demonstrate that our method achieves state-of-the-art results in several downstream tasks.
@article{arxiv.2212.05561,
title = {Using Multiple Instance Learning to Build Multimodal Representations},
author = {Peiqi Wang and William M. Wells and Seth Berkowitz and Steven Horng and Polina Golland},
journal= {arXiv preprint arXiv:2212.05561},
year = {2023}
}