A Visual Question Answering Network Merging High- and Low-Level Semantic Information

Visual Question Answering (VQA) usually uses deep attention mechanisms to learn fine-grained visual content of images and textual content of questions. However, the deep attention mechanism can only learn high-level semantic information while ignoring the impact of the low-level semantic information on answer prediction. For such, we design a High- and Low-Level Semantic Information Network (HLSIN), which employs two strategies to achieve the fusion of high-level semantic information and low-level semantic information. Adaptive weight learning is taken as the first strategy to allow different levels of semantic information to learn weights separately. The gate-sum mechanism is used as the second to suppress invalid information in various levels of information and fuse valid information. On the benchmark VQA-v2 dataset, we quantitatively and qualitatively evaluate HLSIN and conduct extensive ablation studies to explore the reasons behind HLSIN's effectiveness. Experimental results demonstrate that HLSIN significantly outperforms the previous state-of-the-art, with an overall accuracy of 70.93% on test-dev.