Cross-Modality Relevance for Reasoning on Language and Vision
This addresses the problem of cross-modal reasoning for AI systems handling language and vision, with incremental improvements in performance and training efficiency.
The paper tackles the challenge of learning and reasoning over language and vision data for tasks like visual question answering (VQA) and natural language for visual reasoning (NLVR) by introducing a cross-modality relevance module that models higher-order relevance between textual and visual entities and their relations, showing competitive performance on public benchmarks and improving state-of-the-art results.
This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). We design a novel cross-modality relevance module that is used in an end-to-end framework to learn the relevance representation between components of various input modalities under the supervision of a target task, which is more generalizable to unobserved data compared to merely reshaping the original representation space. In addition to modeling the relevance between the textual entities and visual entities, we model the higher-order relevance between entity relations in the text and object relations in the image. Our proposed approach shows competitive performance on two different language and vision tasks using public benchmarks and improves the state-of-the-art published results. The learned alignments of input spaces and their relevance representations by NLVR task boost the training efficiency of VQA task.