Abstract
Visual cognitive development is vital for intelligent robots to handle various types of visual tasks rather than predefined ones. It can transfer the classification ability from an original model to a novel task. However, the high reliance on large amounts of data hinders its development. The energy it costs to adjust to the novel tasks is also a tough problem. Thus we propose a model called knowledge-experience graph (KEG) to imitate the mechanisms of human brains. With the help of social knowledge stored in the knowledge graph, the novel classes can be easily added. The combination of the experience via denoising autoencoder (DAE) also takes the relationship in the visual space into account. With the propagation of information among the graph by graph convolutional network (GCN), KEG generates the classifier of the novel tasks effectively. Experiments show that KEG improves the classification accuracy of novel categories on zero-shot learning and accomplishes visual cognitive development to a certain extent.
This work is supported partly by the National Natural Science Foundation (NSFC) of China (grants 61973301, 61972020, 61633009, and U1613213), partly by the National Key R&D Program of China (grants 2016YFC0300801 and 2017YFB1300202), partly by the Beijing Science and Technology Plan Project, and partly by the Meituan Open R&D Fund.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, X.L., Ye, Y.F., Gupta, A.: Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs. In: CVPR (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, pp. 2121–2129 (2013)
Li, Y., Wang, D., Hu, H., Lin, Y., Zhuang, Y.: Zero-shot recognition using dual visual-semantic mapping paths. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Kampffmeyer, M., Chen, Y., Chen, Y.: Rethinking knowledge graph propagation for zero-shot learning. In: Conference on Computer Vision and Pattern Recognition (2019)
Gidaris, S., Komodakis, N.: Generating classification weights with GNN Denoising Autoencoders for few-shot learning. In: Conference on Computer Vision and Pattern Recognition (2019)
He, K., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.:. Imagenet: a large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Miller, G.A.: Wordnet: a lexical database for english. Commun. ACM 38(11), 39–41 (1995)
Ziming, Z., Saligrama, V.: Zero-shot learning via semantic similarity embedding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4166–4174 (2015)
Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2021–2030 (2017)
Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3174–3183 (2017)
Sung, F., Yongxin, Y., Li, Z., Xiang, T., Torr, P., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)
Changpinyo, S., Wei-Lun, C., Boqing, G., Sha, F.: Synthesized classifiers for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5327–5336 (2016)
Akata, Z., Reed, S., Walter, D., Honglak, L., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2927–2936 (2015)
Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-Shot learning - a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 40(8), 2251–2265 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, X., Yang, X., Liu, Z., Zhang, L., Ren, D., Fan, M. (2020). Knowledge-Experience Graph with Denoising Autoencoder for Zero-Shot Learning in Visual Cognitive Development. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science, vol 1333. Springer, Cham. https://doi.org/10.1007/978-3-030-63823-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-63823-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63822-1
Online ISBN: 978-3-030-63823-8
eBook Packages: Computer ScienceComputer Science (R0)