COIN: Counterfactual Image Generation for VQA Interpretation
This addresses the need for interpretability in VQA systems, which are error-prone with complex questions, by offering a method to understand model decisions, though it is incremental as it builds on existing interpretability techniques.
The paper tackles the problem of interpreting Visual Question Answering (VQA) models by generating counterfactual images with minimal changes to alter the model's answer, and it conducted a user study to evaluate the approach, providing extensive explanations of VQA behavior.
Due to the significant advancement of Natural Language Processing and Computer Vision-based models, Visual Question Answering (VQA) systems are becoming more intelligent and advanced. However, they are still error-prone when dealing with relatively complex questions. Therefore, it is important to understand the behaviour of the VQA models before adopting their results. In this paper, we introduce an interpretability approach for VQA models by generating counterfactual images. Specifically, the generated image is supposed to have the minimal possible change to the original image and leads the VQA model to give a different answer. In addition, our approach ensures that the generated image is realistic. Since quantitative metrics cannot be employed to evaluate the interpretability of the model, we carried out a user study to assess different aspects of our approach. In addition to interpreting the result of VQA models on single images, the obtained results and the discussion provides an extensive explanation of VQA models' behaviour.