In the paper, we consider the task of Visual Question Answering, an important task for creating General Artificial Intelligence (AI) systems. We propose an interpretable model called GS-VQA. The main idea behind it is that a complex compositional question could be decomposed into a sequence of simple questions about objects’ properties and their relations. We use the Unified estimator to answer questions from that sequence and test the proposed model on CLEVR and THOR-VQA datasets. The GS-VQA model demonstrates results comparable to the state of the art while maintaining transparency and interpretability of the response generation process.
Read (PDF) or watch presentation (Google Drive) at the AGI 2022 website: https://agi-conf.org/2022/accepted-posters/
Sarkisyan, C., Savelov, M., Kovalev, A. K., Panov, A. I. (2023). Graph Strategy for Interpretable Visual Question Answering // Artificial General Intelligence. AGI 2022. Lecture Notes in Computer Science, vol 13539, pp. 86–99. https://doi.org/10.1007/978-3-031-19907-3_9