Style-Aware Contrastive Learning for Multi-Style Image Captioning
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-26-2023
- Country:
- South America > Argentina
- Pampas > Buenos Aires F.D. > Buenos Aires (0.04)
- North America
- United States
- Washington > King County
- Seattle (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- New York > New York County
- New York City (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- Los Angeles County > Long Beach (0.04)
- San Diego County > San Diego (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Washington > King County
- Canada
- United States
- Europe
- Switzerland > Zürich
- Zürich (0.14)
- Netherlands > North Holland
- Amsterdam (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- France > Hauts-de-France
- Switzerland > Zürich
- Asia
- South America > Argentina
- Genre:
- Research Report > New Finding (0.48)
- Technology: