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.- Anthology ID:
- 2023.findings-eacl.169
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2257–2267
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.169
- DOI:
- Cite (ACL):
- Yucheng Zhou and Guodong Long. 2023. Style-Aware Contrastive Learning for Multi-Style Image Captioning. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2257–2267, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Style-Aware Contrastive Learning for Multi-Style Image Captioning (Zhou & Long, Findings 2023)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2023.findings-eacl.169.pdf