2020
Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
CVPR 2020poster
Despite significant success in Visual Question Answering (VQA), VQA models have been shown to be notoriously brittle to linguistic variations in the questions. Due to deficiencies in models and datasets, today's models often rely on correlations rather than predictions that are causal w.r.t. data. I…