SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering

Vipul Gupta, Zhuowan Li, Adam Kortylewski +3

While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA mod…