2021
Human-Adversarial Visual Question Answering
Sasha Sheng, Amanpreet Singh, Vedanuj Goswami, Jose Alberto Lopez Magana, Tristan Thrush, Wojciech Galuba +2
NeurIPS 2021poster
Performance on the most commonly used Visual Question Answering dataset (VQA v2) is starting to approach human accuracy. However, in interacting with state-of-the-art VQA models, it is clear that the problem is far from being solved. In order to stress test VQA models, we benchmark them against huma…