More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching
This work addresses the limitation of inaccurate attention models in cross-modal matching, which is important for applications like image search and captioning, but it is incremental as it builds on existing attention-based methods.
The authors tackled the problem of sub-optimal cross-modal attention in image-text matching by proposing two contrastive training constraints (CCR and CCS) that provide direct supervision without explicit annotations, resulting in improved retrieval performance and attention metrics on Flickr30k and MS-COCO datasets.
Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities. However, the cross-modal attention models of existing methods could be sub-optimal and inaccurate because there is no direct supervision provided during the training process. In this work, we propose two novel training strategies, namely Contrastive Content Re-sourcing (CCR) and Contrastive Content Swapping (CCS) constraints, to address such limitations. These constraints supervise the training of cross-modal attention models in a contrastive learning manner without requiring explicit attention annotations. They are plug-in training strategies and can be easily integrated into existing cross-modal attention models. Additionally, we introduce three metrics including Attention Precision, Recall, and F1-Score to quantitatively measure the quality of learned attention models. We evaluate the proposed constraints by incorporating them into four state-of-the-art cross-modal attention-based image-text matching models. Experimental results on both Flickr30k and MS-COCO datasets demonstrate that integrating these constraints improves the model performance in terms of both retrieval performance and attention metrics.