English

Style-Aware Contrastive Learning for Multi-Style Image Captioning

Computer Vision and Pattern Recognition 2023-01-30 v1 Computation and Language

Abstract

Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style. However, existing methods overlook the relationship between linguistic style and visual content. To overcome this drawback, we propose style-aware contrastive learning for multi-style image captioning. First, we present a style-aware visual encoder with contrastive learning to mine potential visual content relevant to style. Moreover, we propose a style-aware triplet contrast objective to distinguish whether the image, style and caption matched. To provide positive and negative samples for contrastive learning, we present three retrieval schemes: object-based retrieval, RoI-based retrieval and triplet-based retrieval, and design a dynamic trade-off function to calculate retrieval scores. Experimental results demonstrate that our approach achieves state-of-the-art performance. In addition, we conduct an extensive analysis to verify the effectiveness of our method.

Keywords

Cite

@article{arxiv.2301.11367,
  title  = {Style-Aware Contrastive Learning for Multi-Style Image Captioning},
  author = {Yucheng Zhou and Guodong Long},
  journal= {arXiv preprint arXiv:2301.11367},
  year   = {2023}
}

Comments

Findings of EACL 2023

R2 v1 2026-06-28T08:22:18.035Z