A one-shot learning algorithm using support set information during training

doi:10.3969/j.issn.0253-2778.2020.08.020

Abstract

Abstract: The purpose of one-shot learning is to use a source category dataset containing a large number of training samples and a target category dataset containing only one training sample per category to construct a learning algorithm that enables accurate classification of samples in the target category space. The existing one-shot learning algorithm mainly uses the source category data to train the model, and then uses the training data of the target category as the support set to realize the classification of the unlabeled samples during the test. Therefore, it fails to effectively utilize the information of the support set during the training. Here, a one-shot learning algorithm using support set information in both the training and test stages is established. The basic idea is to use Siamese neural networks to build models and add support set information during training, that is, to make the similarity between different types of support set samples as small as possible. Experimental results on Omniglot data set and Manchu recognition show that the proposed algorithm can achieve better recognition accuracy.

Key words: one-shot learning, siamese neural networks, metric learning

CLC Number:

TP391.1

XIN Shouyu, ZHENG Ruirui, ZHOU Yu, LIU Wenpeng, HE Jianjun. A one-shot learning algorithm using support set information during training[J]. Journal of University of Science and Technology of China, 2020, 50(8): 1187-1192.

References

［1］
DAI J, QI H, XIONG Y, et al. Deformable convolutional networks[C]// Proceedings of the International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 764-773.
[2] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386-397.
[3] HUANG G, LIU Z, WEINBERGER K Q, et al. Densely connected convolutional networks[C]// Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, United states:IEEE, 2017: 2261-2269.
[4] KRIZHEVSKY A, SUTSKEVER I, HINTON G E, et al. ImageNet classification with deep convolutional neural networks[J]. Communications of The ACM. 2017,60(6):84-90.
[5] LI F F, ROB F, PIETRO P. One-shot learning of object categories[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28 (4):594-611.
[6] LAKE B M, LEE C, GLASS J, et al. One-shot learning of generative speech concepts[J]. Cognitive Science, 2014, 36(36): 803-808.
[7] GREGORY K, RICHARD Z, RUSLAN S. Siamese neural networks for one-shot image recognition[C/OL]// Proceedings of the 32nd International Conference on Machine Learning. Lille, France: JMLR:W&CP, 2015. [2020-05-18]. https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf
[8] VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[C]// Advances in Neural Information Processing Systems 29 - Proceedings of the 2016 Conference. Barcelona, Spain:Neural information processing systems foundation, 2016,0(1): 3637-3645.
[9] SANTORO A, BARTUNOV S, BOTVINICK M, et al. Meta-learning with memory-augmented neural networks[C]// 33rd International Conference on Machine Learning. New York, United states: International Machine Learning Society,2016, 4(4): 2740-2751.
[10] CHEN Z, FU Y, WANG Y , et al. Image deformation Meta-networks for one-shot learning[C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Long Beach, CA, United states: IEEE, 2019: 8672-8681.
[11] LAKE B M, SALAKHUTDINOV R, TENENBAUM J B. Human-level concept learning through probabilistic program induction[J]. Science, 2015,350(6266): 1332-1338.
[12] LAKE B M, SALAKHUTDINOV R, TENENBAUM J B, et al. One-shot learning by inverting a compositional causal process[C]// Neural Information Processing Systems26,NIPS 2013. Lake Tahoe, United states: Neural information processing systems foundation ,2013: 1-9.
[13] SALAKHUTDINOV R, TENENBAUM J, TORRALBA A, et al. One-shot learning with a hierarchical nonparametric Bayesian model[C]// Workshop on Unsupervised and Transfer Learning.Washington: IEEE, 2012: 195-207.
[14] MISHRA N, ROHANINEJAD M, CHEN X, et al. A simple neural attentive meta-learner [C]// 6th International Conference on Learning Representations. Vancouver, Canada: IEEE, 2018: 1-17.
[15] RAVI S, LAROCHELLE H. Optimization as a model for few-shot learning[C]// 5th International Conference on Learning Representations. Toulon, France: IEEE, 2017: 1-11.
[16] YOON J, KIM T, DIA O, et al. Bayesian model-agnostic Meta-learning[C]// Proceedings of the Conference on Advances in Neural Information Processing Systems. Montreal, Canada: Neural information processing systems foundation, 2018, arXiv:1806.03836v4.
[17] FINN C, ABBEEL P, LEVINE S, et al. Model-agnostic Meta-learning for fast adaptation of deep networks[C]// 34th International Conference on Machine Learning. Sydney, Australia: IMLS, 2017, 3(8):1856-1868.
[18] NICHOL A, ACHIAM J, SCHULMAN J, et al. On first-order Meta-learning algorithms.[J/OL]. 2018, arXiv: abs/1803.02999.
[19] SHABAN A, BANSAL S, LIU Z, et al. One-shot learning for semantic segmentation[C]// British Machine Vision Conference 2017. London, United Kingdom: BMVA Press, 2017, arXiv:1709.03410.
[20] CAI Q, PAN Y, YAO T, et al. Memory matching networks for one-shot image recognition[C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Salt Lake City, United states: IEEE Computer Society, 2018:4080-4088.
[21] SNELL J, SWERSKY K, ZEMEL R S, et al. Prototypical networks for few-shot learning[C]// Advances in Neural Information Processing Systems. Long Beach, United states: IEEE, 2017: 4078-4088.
[22] SUNG F, YANG Y, ZHANG L, et al. Learning to compare: Relation network for few-shot learning[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, United states: IEEE Computer Society, 2018: 1199-1208.

