Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
This work aims to improve the quality of image captions by enhancing the global understanding of images for Transformer-based models, which is an incremental improvement for the image captioning community.
This paper addresses the limitation of region-level information in Transformer-based image captioning by introducing a Global Enhanced Transformer (GET). GET extracts and leverages a more comprehensive global representation of the entire image, leading to superior performance on the MS COCO dataset compared to state-of-the-art methods.
Transformer-based architectures have shown great success in image captioning, where object regions are encoded and then attended into the vectorial representations to guide the caption decoding. However, such vectorial representations only contain region-level information without considering the global information reflecting the entire image, which fails to expand the capability of complex multi-modal reasoning in image captioning. In this paper, we introduce a Global Enhanced Transformer (termed GET) to enable the extraction of a more comprehensive global representation, and then adaptively guide the decoder to generate high-quality captions. In GET, a Global Enhanced Encoder is designed for the embedding of the global feature, and a Global Adaptive Decoder are designed for the guidance of the caption generation. The former models intra- and inter-layer global representation by taking advantage of the proposed Global Enhanced Attention and a layer-wise fusion module. The latter contains a Global Adaptive Controller that can adaptively fuse the global information into the decoder to guide the caption generation. Extensive experiments on MS COCO dataset demonstrate the superiority of our GET over many state-of-the-arts.