Abstract
How to generalize and unify different few-shot learning tasks using neural network model is a difficult problem in the field of machine learning research. Aiming at the problem that the parameters of existing few-shot learning models cannot adapt with heterogeneous classification tasks, inspired by the human being recognition process, a hybrid neural network (HNN) model for large-scale heterogeneous classification tasks in few-shot learning is proposed. First, a meta-learning model is constructed, which uses a siamese graph convolutional network (SGCN) structure as bone network. The SGCN is trained by semi-supervised way with a small amount of incomplete labeled data. Then, random task slicing by group is performed according to the task size and meta-learning dimensions to ensure that the segmented task size matches the meta-learning model. Combined with the meta-learning model, a task discrimination network and object recognition network are constructed, to perform heterogeneous classification tasks while keeping the scale of HNN network parameters unchanged. Experimental results show that the HNN performs well under different datasets, and is suitable for large-scale heterogeneous tasks in few-shot learning without retraining.
Similar content being viewed by others
References
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Mohammadi, M., Al-Fuqaha, A., Sorour, S., et al.: Deep learning for IoT big data and streaming analytics: a survey. IEEE Commun. Surv. Tutor. 20(4), 2923–2960 (2018)
Jallad, K.A., Aljnidi, M., Desouki, S., et al.: Big data analysis and distributed deep learning for next-generation intrusion detection system optimization. J. Big Data 6(1), 1–18 (2019)
Konstantinos, M., Konstantinos, K., Anastasios, D., et al.: Deep supervised learning for hyperspectral data classification through convolutional neural networks. In: 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Carneiro, G., Chan, A.B., Moreno, P.J., et al.: Supervised learning of semantic classes for image annotation and retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 394–410 (2007)
Li, X., Shen, H., Zhang, L., et al.: Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning. IEEE Trans. Geosci. Remote Sens. 52(11), 7086–7098 (2014)
Lake, B., Salakhutdinov, R., Gross, J, et al.: One shot learning of simple visual concepts. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 33(33) (2011)
Ma, Y., Kan, M., Shan, S., et al.: Learning deep face representation with long-tail data: an aggregate-and-disperse approach. Pattern Recogn. Lett. 133, 48–54 (2020)
Wang, D., Cheng, Y., Yu, M., et al.: A hybrid approach with optimization-based and metric-based meta-learner for few-shot learning. Neurocomputing 349, 202–211 (2019)
Tian, S., Shen, S., Tian, G., et al.: End-to-end deep metric network for visual tracking. Vis. Comput. 36(6), 1219–1232 (2020)
Blaes, S., Burwick, T.: Few-shot learning in deep networks through global prototyping. Neural Netw. 94, 159–172 (2017)
Wu, H., Miao, Z., Wang, Y., et al.: Optimized recognition with few instances based on semantic distance. Vis. Comput. 31(4), 367–375 (2015)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2 (2015)
Oriol, V., Charles, B., Tim, L., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, pp. 3630–3638 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)
Sung, F., Yang, Y., Zhang, L., et al.: 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)
Santoro, A., Bartunov, S., Botvinick, M., et al.: Meta-learning with memory-augmented neural networks. In: International Conference on Machine Learning, pp. 1842-1850 (2016)
Sun, Q., Liu, Y., Chua, T.S., et al.: Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 403–412 (2019)
Tang, H., Li, Z., Peng, Z., et al.: BlockMix: meta regularization and self-calibrated inference for metric-based meta-learning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 610–618 (2020)
Peng, Z., Li, Z., Zhang, J., et al.: Few-shot image recognition with knowledge transfer. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 441-449 (2019)
Jiang, L.B., Zhou, X.L., Jiang, W., et al.: One shot learning based on improved matching network. Syst. Eng. Electron. 41(6), 1210–1217 (2019)
Yu, Y., Feng, L., Wang, G.G., et al.: A Few-Shot learning model based on semisupervised with pseudo label. Acta Electron. Sin. 47(11), 2284–2291 (2019)
Zhang, L., Chang, X., Liu, J., et al.: Few-shot activity recognition with cross-modal memory network. Pattern Recogn. 108, 107348 (2020)
Ji, Z., Chai, X., Yu, Y., et al.: Improved prototypical networks for Few-Shot learning. Pattern Recogn. Lett. 140, 81–87 (2020)
Garcia, V., Bruna, J.: Few-shot learning with graph neural networks. In: 6th International Conference on Learning Representations, ICLR, Vancouver, BC, Canada (2018)
Shen, J., Tang, X., Dong, X., et al.: Visual object tracking by hierarchical attention siamese network. IEEE Trans. Cybern. 50(7), 3068–3080 (2019)
Liang, Z., Shen, J.: Local semantic siamese networks for fast tracking. IEEE Trans. Image Process. 29, 3351–3364 (2019)
Dong, X., Shen, J., Wu, D., et al.: Quadruplet network with one-shot learning for fast visual object tracking. IEEE Trans. Image Process. 28(7), 3516–3527 (2019)
Kim, J., Kim, T., Kim, S., et al.: Edge-labeling graph neural network for fewshot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11–20 (2019)
Dong, X., Shen, J.: Triplet loss in siamese network for object tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 459–474 (2018)
Qian, K., Song, A.G.: An improved bionic cognitive neural network for robot. Chin. J. Electron. 43(6), 1084–1089 (2015)
Scarselli, F., Gori, M., Tsoi, A.C., et al.: Computational capabilities of graph neural networks. IEEE Trans. Neural Netw. 20(1), 81–102 (2008)
Wang, W., Lu, X., Shen, J., et al.: Zero-shot video object segmentation via attentive graph neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9236–9245 (2019)
Qi, S., Wang, W., Jia, B., et al. Learning human-object interactions by graph parsing neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 401–417 (2018)
Phan, A.V., Le Nguyen, M., Nguyen, Y.L.H., et al.: DGCNN: a convolutional neural network over large-scale labeled graphs. Neural Netw. 108, 533–543 (2018)
Fan, H., Zhong, Y., Zeng, G., et al.: Attributed network representation learning via improved graph attention with robust negative sampling. Appl. Intell. 4, 1–11 (2020)
Yin, J., Shen, J., Guan, C., et al.: LiDAR-based online 3D video object detection with graph-based message passing and spatiotemporal transformer attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11495–11504 (2020)
Rahman, S., Khan, S., Porikli, F.: A unified approach for conventional zeroshot, generalized zero-shot, and few-shot learning. IEEE Trans. Image Process. 27(11), 5652–5667 (2018)
Acknowledgements
This paper was supported by Nanjing Institute of Technology High-level Scientific Research Foundation for the introduction of talent (No. YKJ201918) and the Natural Science Foundation of the Jiangsu Higher Education Institutions of China (No. 20KJB510049), partially supported by the National Key R&D Program of China (No.2017YFB1002802) and National Natural Science Foundation of China (No.51675259).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qian, K., Wen, X. & Song, A. Hybrid neural network model for large-scale heterogeneous classification tasks in few-shot learning. Vis Comput 38, 719–728 (2022). https://doi.org/10.1007/s00371-020-02046-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-020-02046-6