On the Human-level Performance of Visual Question Answering

AbstractVisual7W has been widely used in assessing multiple-choice visual question-answering (VQA) systems. This paper reports on a replicated human experiment on Visual7W with the aim of understanding the human-level performance of VQA. The replication was not entirely successful because human participants performed significantly worse when answering “where”, “when”, and “how” questions in compared to other question types. An error analysis discovered that the failure was a consequence of the non-deterministic distractors in Visual7W. GPT-4V was then evaluated using and was compared to the human-level performance. The results embody that, when evaluating models’ capacity on Visual7W, the performance is not necessarily the higher, the better.