Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
arXiv:2012.07061
Abstract
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.
Accepted at AAAI 2021 (preprint version)
References in corpus (10)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Sequence to Sequence Learning with Neural Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Axiomatic Attribution for Deep Networks
- Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- Show, Recall, and Tell: Image Captioning with Recall Mechanism
- Multi-layer Representation Fusion for Neural Machine Translation
- Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
- Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets