Style-Aware Contrastive Learning for Multi-Style Image Captioning
This work improves multi-style image captioning for applications requiring diverse linguistic outputs, but it is incremental as it builds on existing methods by incorporating style-aware contrastive learning.
The paper tackles the problem of multi-style image captioning by addressing the overlooked relationship between linguistic style and visual content, achieving state-of-the-art performance as demonstrated in experiments.
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.