# Towards Transparent AI Systems: Interpreting Visual Question Answering Models Source: [Towards Transparent AI Systems: Interpreting Visual Question Answering Models]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:26:18.516Z Authors: Yash Goyal, Akrit Mohapatra, Devi Parikh, Dhruv Batra Published: 2016-08-31T18:11:29.000Z ## Abstract Deep neural networks have shown striking progress and obtained state-of-the-art results in many AI research fields in the recent years. However, it is often unsatisfying to not know why they predict what they do. In this paper, we address the problem of interpreting Visual Question Answering (VQA) models. Specifically, we are interested in finding what part of the input (pixels in images or words in questions) the VQA model focuses on while answering the question. To tackle this problem, we use two visualization techniques -- guided backpropagation and occlusion -- to find important words in the question and important regions in the image. We then present qualitative and quantitative analyses of these importance maps. We found that even without explicit attention mechanisms, VQA models may sometimes be implicitly attending to relevant regions in the image, and often to appropriate words in the question. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()