One-shot learning based on improved matching network

被引：3
|
作者：
Jiang L. [1 ,3 ]
Zhou X. [2 ,3 ]
Jiang F. [2 ,3 ]
Che L. [1 ,3 ]
机构：
[1] School of Computer and Information Security, Guilin University of Electronic Technology, Guilin
[2] School of Information and Communication, Guilin University of Electronic Technology, Guilin
[3] Key Laboratory of Wireless Broadband Communication and Signal Processing in Guangxi, Guilin University of Electronic Technology, Guilin
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2019年 / 41卷 / 06期
关键词：
Deep learning; Few-shot; Improved matching network; LSTM; Squared Euclidean distance;
D O I：
10.3969/j.issn.1001-506X.2019.06.06
中图分类号：
学科分类号：
摘要：
The current deep learning is based on a large number of labeled data samples to automatically identify the model through a multi-layer network. However, in many special scenarios, it is difficult to obtain a large amount of sample data, and the identification of few-shot learning is still a key problem in deep learning. To solve this problem, the four-layer deep convolutional neural network (DCNN) is first used to extract the high-level semantic features of the training samples and the test samples. Then use the bi-directional LSTM and attLSTM algorithms for further extraction and code of more critical and useful features of training samples and test samples based on the improved matching network. Finally, the softmax nonlinear classifier is used to classify the test samples on the squared euclidean distance. The experiment tests on the proposed improved model with the Omniglot data set and achieves very good results. The improved model can achieve a 93.2% recognition rate even in the most complicated 20-way 1-shot case, and the original matching network model of Vinyals only achieve 88.2% recognition in the case of 20-way 1-shot. Compared with the original matching network model, the improved model has a better recognition effect in a complex scenario with more categories and fewer samples. © 2019, Editorial Office of Systems Engineering and Electronics. All right reserved.
引用
收藏
页码：1210 / 1217
页数：7
相关论文
共 21 条
  • [1] Fei-Fei L., Fergus R., Perona P., One-shot learning of object categories, IEEE Trans. on Pattern Analysis and Machine Intelligence, 28, 4, pp. 594-611, (2006)
  • [2] Lake B.M., Salakhutdinov R., Tenenbaum J.B., Human-level concept learning through probabilistic program induction, Science, 350, 6266, pp. 1332-1338, (2015)
  • [3] Vinyals O., Blundell C., Lillicrap T., Et al., Matching networks for one shot learning, Proc. of the Advances in Neural Information Processing Systems, pp. 3630-3638, (2016)
  • [4] Snell J., Swersky K., Zemel R., Prototypical networks for few-shot learning, Proc. of the Advances in Neural Information Processing Systems, pp. 4080-4090, (2017)
  • [5] Ravi S., Larochelle H., Optimization as a model for few-shot learning, Proc. of the International Conference on Learning Represention, pp. 1-11, (2017)
  • [6] Munkhdalai T., Yu H., Meta networks, Proc. of the International Conference on Machine Learning, pp. 2554-2563, (2017)
  • [7] Simard P.Y., Steinkraus D., Platt J.C., Best practices for convolutional neural networks applied to visual document analysis, Proc. of the 7th International Conference on Document Analysis and Recognition, 3, pp. 958-962, (2003)
  • [8] Keshari R., Vatsa M., Singh R., Et al., Learning structure and strength of CNN filters for small sample size training, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9349-9358, (2018)
  • [9] Duan M., Li K., Yang C., Et al., A hybrid deep learning CNN-ELM for age and gender classification, Neuro Computing, 275, pp. 448-461, (2018)
  • [10] Koch G., Zemel R., Salakhutdinov R., Siamese neural networks for one-shot image recognition, Proc. of the ICML Deep Learning Workshop, (2015)
123