English

JECL: Joint Embedding and Cluster Learning for Image-Text Pairs

Machine Learning 2020-10-20 v3 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}

Comments

ICPR2020

R2 v1 2026-06-23T07:04:51.194Z