Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
This work addresses the problem of noisy reasoning in FVQA for AI systems requiring external knowledge, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of fact-based visual question answering (FVQA) by proposing a multi-layer cross-modal knowledge reasoning model that uses a modality-aware heterogeneous graph convolutional network to select and aggregate relevant evidence from visual, semantic, and factual features, achieving a new state-of-the-art performance on the FVQA task.
Fact-based Visual Question Answering (FVQA) requires external knowledge beyond visible content to answer questions about an image, which is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the final answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features. On top of the multi-layer graph representations, we propose a modality-aware heterogeneous graph convolutional network to capture evidence from different layers that is most relevant to the given question. Specifically, the intra-modal graph convolution selects evidence from each modality and cross-modal graph convolution aggregates relevant information across different modalities. By stacking this process multiple times, our model performs iterative reasoning and predicts the optimal answer by analyzing all question-oriented evidence. We achieve a new state-of-the-art performance on the FVQA task and demonstrate the effectiveness and interpretability of our model with extensive experiments.