Learning Conditioned Graph Structures for Interpretable Visual Question Answering
This addresses the challenge of interpretable visual question answering for AI systems, though it appears incremental as it builds on existing graph convolution concepts.
The paper tackles the problem of visual question answering by proposing a graph-based approach that learns question-specific graph representations of images to capture semantic and spatial relationships, achieving 66.18% accuracy on the VQA v2 dataset and demonstrating interpretability.
Visual Question answering is a challenging problem requiring a combination of concepts from Computer Vision and Natural Language Processing. Most existing approaches use a two streams strategy, computing image and question features that are consequently merged using a variety of techniques. Nonetheless, very few rely on higher level image representations, which can capture semantic and spatial relationships. In this paper, we propose a novel graph-based approach for Visual Question Answering. Our method combines a graph learner module, which learns a question specific graph representation of the input image, with the recent concept of graph convolutions, aiming to learn image representations that capture question specific interactions. We test our approach on the VQA v2 dataset using a simple baseline architecture enhanced by the proposed graph learner module. We obtain promising results with 66.18% accuracy and demonstrate the interpretability of the proposed method. Code can be found at github.com/aimbrain/vqa-project.