Boosted Attention: Leveraging Human Attention for Image Captioning
This work addresses the challenge of improving attention accuracy in image captioning models, which is incremental as it builds on existing attention methods.
The paper tackled the problem of visual attention in image captioning by integrating both top-down and bottom-up attention mechanisms, achieving state-of-the-art performance across various metrics.
Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly by optimizing the captioning objectives. While somewhat effective, the learned top-down attention can fail to focus on correct regions of interest without direct supervision of attention. Inspired by the human visual system which is driven by not only the task-specific top-down signals but also the visual stimuli, we in this work propose to use both types of attention for image captioning. In particular, we highlight the complementary nature of the two types of attention and develop a model (Boosted Attention) to integrate them for image captioning. We validate the proposed approach with state-of-the-art performance across various evaluation metrics.