An increasing amount of studies have investigated the decision-making process of VQA models. Many of these studies focus on the reason behind the correct answer chosen by a model. Yet, the reason why the distracting answer chose by a model has rarely been studied. To this end, we introduce a novel task called \textit{textual Distractors Generation for VQA} (DG-VQA) that explaining the decision boundaries of existing VQA models. The goal of DG-VQA is to generate the most confusing set of textual distractors in multi-choice VQA tasks which expose the vulnerability of existing models (i.e. to generate distractors that lure existing models to fail). We show that DG-VQA can be formulated as a Markov Decision Process, and present a reinforcement learning solution to come up with distractors in an unsupervised manner. The solution addresses the lack of large annotated corpus issues in previous distractor generation methods. Our proposed model receives reward signals from fully-trained multi-choice VQA models and updates its parameters via policy gradient. The empirical results show that the generated textual distractors can successfully attack several popular VQA models with an average $20\%$ accuracy drop from $64\%$. Furthermore, we conduct adversarial training to improve the robustness of VQA models by incorporating the generated distractors. Empirical results validate the effectiveness of adversarial training by showing a performance improvement of $27\%$ for the multi-choice VQA task.
翻译:越来越多的研究调查了VQA模式的决策过程。许多这些研究侧重于一个模型所选正确答案背后的原因。然而,一个模型所选择的转移注意力的答案很少被研究。为此,我们引入了一个叫作\textit{texttractitors Dongering for VQA}(DG-VQA)的新颖任务,解释现有VQA模式的决策界限。DG-VQA的目标是在多选择VQA任务中产生最令人困惑的文本干扰者,这暴露了现有模型的脆弱性(即产生分散注意力者,诱导现有模型失败)。我们显示DG-VQA可以作为Markov的决策过程,提出一种强化的学习解决方案,以不受监督的方式解决现有VQA模式的决策范围。DG-VQA的目标是从经过充分训练的多选择性VQA模型中产生最令人困惑的奖赏信号,并通过政策梯度更新其参数。我们的经验性结果显示,DG-VQQA的快速性变校程模型可以显示,我们通过高性变校程的变校程的变校程模型可以成功地改进。