Why Does a Visual Question Have Different Answers?

Nilavra Bhattacharya, Qing Li, Danna Gurari; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 4271-4280

Visual question answering is the task of returning the answer to a question about an image. A challenge is that different people often provide different answers to the same visual question. To our knowledge, this is the first work that aims to understand why. We propose a taxonomy of nine plausible reasons, and create two labelled datasets consisting of 45,000 visual questions indicating which reasons led to answer differences. We then propose a novel problem of predicting directly from a visual question which reasons will cause answer differences as well as a novel algorithm for this purpose. Experiments demonstrate the advantage of our approach over several related baselines on two diverse datasets. We publicly share the datasets and code at https://vizwiz.org.