We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is expensive to produce, but free-text descriptions are common. JECL trains by minimizing the Kullback-Leibler divergence between the distribution of the images and text to that of a combined joint target distribution and optimizing the Jensen-Shannon divergence between the soft cluster assignments of the images and text. Regularizers are also applied to JECL to prevent trivial solutions. Experiments show that JECL outperforms both single-view and multi-view methods on large benchmark image-caption datasets, and is remarkably robust to missing captions and varying data sizes.
@article{arxiv.1901.01860,
title = {JECL: Joint Embedding and Cluster Learning for Image-Text Pairs},
author = {Sean T. Yang and Kuan-Hao Huang and Bill Howe},
journal= {arXiv preprint arXiv:1901.01860},
year = {2020}
}