Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering

1 code implementation • EMNLP 2020 • Zujie Liang, Weitao Jiang, Haifeng Hu, Jiaying Zhu

In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn spurious correlations in the training set and achieve poor performance in out-of-distribution test data.

Contrastive Learning counterfactual +2