MUREL: Multimodal Relational Reasoning for Visual Question Answering
This addresses the need for better reasoning capabilities in VQA tasks, offering a novel approach that improves performance over existing methods, though it is incremental in advancing relational modeling.
The paper tackles the problem of complex reasoning in Visual Question Answering (VQA) by proposing MuRel, a multimodal relational network that models interactions between questions and image regions, and it outperforms attention-based methods on datasets like VQA 2.0, VQA-CP v2, and TDIUC.
Multimodal attentional networks are currently state-of-the-art models for Visual Question Answering (VQA) tasks involving real images. Although attention allows to focus on the visual content relevant to the question, this simple mechanism is arguably insufficient to model complex reasoning features required for VQA or other high-level tasks. In this paper, we propose MuRel, a multimodal relational network which is learned end-to-end to reason over real images. Our first contribution is the introduction of the MuRel cell, an atomic reasoning primitive representing interactions between question and image regions by a rich vectorial representation, and modeling region relations with pairwise combinations. Secondly, we incorporate the cell into a full MuRel network, which progressively refines visual and question interactions, and can be leveraged to define visualization schemes finer than mere attention maps. We validate the relevance of our approach with various ablation studies, and show its superiority to attention-based methods on three datasets: VQA 2.0, VQA-CP v2 and TDIUC. Our final MuRel network is competitive to or outperforms state-of-the-art results in this challenging context. Our code is available: https://github.com/Cadene/murel.bootstrap.pytorch