Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering
This addresses the challenge of answering complex questions requiring multi-hop reasoning in knowledge-based visual QA, which is incremental as it builds on existing methods by introducing hypergraphs for better semantic encoding.
The paper tackles the problem of multi-hop reasoning for knowledge-based visual question answering under weak supervision, where no supervision is given for the reasoning process. It introduces a Hypergraph Transformer model that constructs hypergraphs to encode high-level semantics and learns associations, achieving effectiveness in experiments on visual and textual QA datasets.
Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed model, Hypergraph Transformer, constructs a question hypergraph and a query-aware knowledge hypergraph, and infers an answer by encoding inter-associations between two hypergraphs and intra-associations in both hypergraph itself. Extensive experiments on two knowledge-based visual QA and two knowledge-based textual QA demonstrate the effectiveness of our method, especially for multi-hop reasoning problem. Our source code is available at https://github.com/yujungheo/kbvqa-public.