Exploring and Distilling Cross-Modal Information for Image Captioning
This work addresses the problem of generating more accurate and coherent image captions for applications in computer vision and AI, representing an incremental improvement over existing attention-based methods.
The paper tackles the challenge of achieving deep image understanding in captioning by proposing a cross-modal approach that globally and locally explores and distills visual and semantic information, resulting in a CIDEr score of 129.3 on the COCO test set with high efficiency.
Recently, attention-based encoder-decoder models have been used extensively in image captioning. Yet there is still great difficulty for the current methods to achieve deep image understanding. In this work, we argue that such understanding requires visual attention to correlated image regions and semantic attention to coherent attributes of interest. Based on the Transformer, to perform effective attention, we explore image captioning from a cross-modal perspective and propose the Global-and-Local Information Exploring-and-Distilling approach that explores and distills the source information in vision and language. It globally provides the aspect vector, a spatial and relational representation of images based on caption contexts, through the extraction of salient region groupings and attribute collocations, and locally extracts the fine-grained regions and attributes in reference to the aspect vector for word selection. Our Transformer-based model achieves a CIDEr score of 129.3 in offline COCO evaluation on the COCO testing set with remarkable efficiency in terms of accuracy, speed, and parameter budget.