The task of Visual Question Answering (VQA) is known to be plagued by the issue of VQA models exploiting biases within the dataset to make its final prediction. Various previous ensemble based debiasing methods have been proposed where an additional model is purposefully trained to be biased in order to train a robust target model. However, these methods compute the bias for a model simply from the label statistics of the training data or from single modal branches. In this work, in order to better learn the bias a target VQA model suffers from, we propose a generative method to train the bias model directly from the target model, called GenB. In particular, GenB employs a generative network to learn the bias in the target model through a combination of the adversarial objective and knowledge distillation. We then debias our target model with GenB as a bias model, and show through extensive experiments the effects of our method on various VQA bias datasets including VQA-CP2, VQA-CP1, GQA-OOD, and VQA-CE, and show state-of-the-art results with the LXMERT architecture on VQA-CP2.

翻译：视觉问答（VQA）任务因模型利用数据集中的偏差进行最终预测而广受困扰。此前多种基于集成的去偏差方法被提出，其中额外模型会被刻意训练为带有偏差，以训练一个鲁棒的目标模型。然而，这些方法仅通过训练数据的标签统计或单模态分支来计算模型的偏差。为进一步学习目标VQA模型所承受的偏差，本文提出一种生成式方法来直接从目标模型训练偏差模型，称为GenB。具体而言，GenB采用生成网络，通过对抗目标与知识蒸馏的结合来学习目标模型中的偏差。随后，我们以GenB作为偏差模型对目标模型进行去偏处理，并通过大量实验展示了该方法在多种VQA偏差数据集（包括VQA-CP2、VQA-CP1、GQA-OOD和VQA-CE）上的效果，表明基于LXMERT架构的模型在VQA-CP2上取得了最优结果。