Abstract
The predominant approach of visual question answering (VQA) relies on encoding the image and question with a “black box" neural encoder and decoding a single token into answers such as “yes” or “no”. Despite this approach’s strong quantitative results, it struggles to come up with human-readable forms of justification for the prediction process. To address this insufficiency, we propose LRRA [Look, Read, Reasoning,Answer], a transparent neural-symbolic framework for visual question answering that solves the complicated problem in the real world step-by-step like humans and provides human-readable form of justification at each step. Specifically, LRRA learns to first convert an image into a scene graph and parse a question into multiple reasoning instructions. It then executes the reasoning instructions one at a time by traversing the scene graph using a recurrent neural-symbolic execution module. Finally, it generates answers to the given questions and makes corresponding marks on the image. Furthermore, we believe that the relations between objects in the question is of great significance for obtaining the correct answer, so we create a perturbed GQA test set by removing linguistic cues (attributes and relations) in the questions to analyze which part of the question contributes more to the answer. Our experiments on the GQA dataset show that LRRA is significantly better than the existing representative model (57.12% vs. 56.39%). Our experiments on the perturbed GQA test set show that the relations between objects is more important for answering complicated questions than the attributes of objects.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tan, H., Bansal, M.: LXMERT: Learning cross-modality encoder representations from transformers. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5100–5111. Hong Kong, China, Association for Computational Linguistics, November 2019
Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Antol, S., et al.: Vqa: visual question answering. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2425–2433 (2015)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in VGA matter: elevating the role of image understanding in visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6325–6334 (2017)
Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1955–1960, Austin, Texas, Association for Computational Linguistics November 2016
Hudson, D.A., Manning, C.D.: Gqa: a new dataset for real-world visual reasoning and compositional question answering. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Johnson, J., Hariharan, B., Maaten, L., Li, F.F., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Santoro, A., et al.: A simple neural network module for relational reasoning. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates Inc., Red Hook (2017)
Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Visual reasoning with a general conditioning layer, Courville. Film (2017)
Hudson, D.A., Manning. C.D.: Compositional attention networks for machine reasoning. In :International Conference on Learning Representations (ICLR) (2018)
Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 39–48 (2016)
Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko. K.: Learning to reason: end-to-end module networks for visual question answering. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 804–813 (2017)
Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3008–3017 (2017)
Mascharka, D., Tran, P., Soklaski, R., Majumdar, A.: Transparency by design: casing the gap between performance and interpretability in visual reasoning. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4942–4950 (2018)
Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. In: European Conference on Computer Vision (2018)
Yi, K., et al.: Disentangling reasoning from vision and language understanding. In: Bengio, S., et al. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates Inc., Red Hook (2018)
Johnson, J., et al.: Image retrieval using scene graphs. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3668–3678 (2015)
Teney, D., Liu, L., Hengel. A.: Graph-structured representations for visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Yin, X., Ordonez. V.: Obj2text: generating visually descriptive language from object layouts (2017)
Xu, D., Zhu, Y., Choy, C., Fei-Fei, L.: Scene graph generation by iterative message passing. In :Computer Vision and Pattern Recognition (CVPR) (2017)
Zellers, R., Yatskar, M., Thomson, S., Choi. Y.: Neural motifs: scene graph parsing with global context. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5831–5840 (2018)
Li, Y., Ouyang, W., Zhou, B., Cui, Y., Wang, X.: Factorizable net: an efficient subgraph-based framework for scene graph generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision– ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol. 11205, Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_21
He, K., Zhang, X., Ren, S., Sun. J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Battaglia, P.W.: Relational inductive biases, deep learning, and graph networks (2018)
Xu, K., Hu, W., Leskovec, J., Jegelka. S.: How powerful are graph neural networks? (2018)
Liang, W., Tian, Y., Chen, C., Yu. Z.: Moss: end-to-end dialog system framework with modular supervision (2019)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CON: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Chen, W., Gan, Z., Li, L., Cheng, L., Wang, W., Liu, J.: Meta module network for compositional visual reasoning (2019)
Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077–6086 (2018)
Hu, R., Rohrbach, A., Darrell, T., Saenko, K.: Language-conditioned graph networks for relational reasoning. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10293–10302 (2019)
Acknowledgements
The research work descried in this paper has been supported by the National Nature Science Foundation of China(Contract 61876198, 61976015, 61976016). The authors would like to thank the anonymous reviewers for their valuable comments and suggestions to improve this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wan, Z., Chen, K., Zhang, Y., Xu, J., Chen, Y. (2021). LRRA:A Transparent Neural-Symbolic Reasoning Framework for Real-World Visual Question Answering. In: Li, S., et al. Chinese Computational Linguistics. CCL 2021. Lecture Notes in Computer Science(), vol 12869. Springer, Cham. https://doi.org/10.1007/978-3-030-84186-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-84186-7_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84185-0
Online ISBN: 978-3-030-84186-7
eBook Packages: Computer ScienceComputer Science (R0)