Weakly supervised cross-domain alignment with optimal transport

Siyang Yuan, Ke Bai, Liqun Chen, Yizhe Zhang, Chenyang Tao, Chunyuan Li, Guoyin Wang, Ricardo Henao, Lawrence Carin

Research output: Contribution to journalArticlepeer-review

Abstract

Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural language processing. This paper investigates a novel approach for the identification and optimization of fine-grained semantic similarities between image and text entities, under a weakly-supervised setup, improving performance over state-of-the-art solutions. Our method builds upon recent advances in optimal transport (OT) to resolve the cross-domain matching problem in a principled manner. Formulated as a drop-in regularizer, the proposed OT solution can be efficiently computed and used in combination with other existing approaches. We present empirical evidence to demonstrate the effectiveness of our approach, showing how it enables simpler model architectures to outperform or be comparable with more sophisticated designs on a range of vision-language tasks.
Original languageEnglish (US)
JournalArxiv preprint
StatePublished - Aug 14 2020
Externally publishedYes

Keywords

  • cs.CV

Fingerprint Dive into the research topics of 'Weakly supervised cross-domain alignment with optimal transport'. Together they form a unique fingerprint.

Cite this