Global Fusion Attention for Vision and Language Understanding (Student Abstract)

We extend the popular transformer architecture to a multimodal model, processing both visual and textual inputs. We propose a new attention mechanism on Transformer-based architecture for the joint vision and language understanding tasks. Our model fuses multi-level comprehension between images and texts in a weighted manner, which could better curve the internal relationships. Experiments on benchmark VQA dataset CLEVR demonstrate the effectiveness of the proposed attention mechanism. We also observe the improvements in sample efficiency of reinforcement learning through the experiments on grounded language understanding tasks of BabyAI platform.

Authors

• Zixin Guo
• Chen Liang Shenzhen Geim Graphene Center, Institute of Materials Research, Tsinghua Shenzhen International Graduate School, Tsinghua University
• Ziyu Wan
• Yang Bai

Keywords

No keywords are indexed for this paper.