Multi-Modal Answer Validation for Knowledge-Based VQA


  • Jialin Wu UT Austin
  • Jiasen Lu Allen Institute for AI
  • Ashish Sabharwal Allen Institute for AI
  • Roozbeh Mottaghi Allen Institute for AI



Computer Vision (CV)


The problem of knowledge-based visual question answering involves answering questions that require external knowledge in addition to the content of the image. Such knowledge typically comes in various forms, including visual, textual, and commonsense knowledge. Using more knowledge sources increases the chance of retrieving more irrelevant or noisy facts, making it challenging to comprehend the facts and find the answer. To address this challenge, we propose Multi-modal Answer Validation using External knowledge (MAVEx), where the idea is to validate a set of promising answer candidates based on answer-specific knowledge retrieval. Instead of searching for the answer in a vast collection of often irrelevant facts as most existing approaches do, MAVEx aims to learn how to extract relevant knowledge from noisy sources, which knowledge source to trust for each answer candidate, and how to validate the candidate using that source. Our multi-modal setting is the first to leverage external visual knowledge (images searched using Google), in addition to textual knowledge in the form of Wikipedia sentences and ConceptNet concepts. Our experiments with OK-VQA, a challenging knowledge-based VQA dataset, demonstrate that MAVEx achieves new state-of-the-art results. Our code is available at




How to Cite

Wu, J., Lu, J., Sabharwal, A., & Mottaghi, R. (2022). Multi-Modal Answer Validation for Knowledge-Based VQA. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 2712-2721.



AAAI Technical Track on Computer Vision III