Counterfactual Samples Synthesizing for Robust Visual Question Answering

Long Chen, Xin Yan, Jun Xiao, Hanwang Zhang, Shiliang Pu, Yueting Zhuang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 10800-10809


Despite Visual Question Answering (VQA) has realized impressive progress over the last few years, today's VQA models tend to capture superficial linguistic correlations in the train set and fail to generalize to the test set with different QA distributions. To reduce the language biases, several recent works introduce an auxiliary question-only model to regularize the training of targeted VQA model, and achieve dominating performance on VQA-CP. However, since the complexity of design, current methods are unable to equip the ensemble-based models with two indispensable characteristics of an ideal VQA model: 1) visual-explainable: the model should rely on the right visual regions when making decisions. 2) question-sensitive: the model should be sensitive to the linguistic variations in question. To this end, we propose a model-agnostic Counterfactual Samples Synthesizing (CSS) training scheme. The CSS generates numerous counterfactual training samples by masking critical objects in images or words in questions, and assigning different ground-truth answers. After training with the complementary samples (ie, the original and generated samples), the VQA models are forced to focus on all critical objects and words, which significantly improves both visual-explainable and question-sensitive abilities. In return, the performance of these models is further boosted. Extensive ablations have shown the effectiveness of CSS. Particularly, by building on top of the model LMH, we achieve a record-breaking performance of 58.95% on VQA-CP v2, with 6.5% gains.

Related Material

[pdf] [arXiv]
author = {Chen, Long and Yan, Xin and Xiao, Jun and Zhang, Hanwang and Pu, Shiliang and Zhuang, Yueting},
title = {Counterfactual Samples Synthesizing for Robust Visual Question Answering},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}