Abstract
Overfitting is an inherent problem in few-shot learning. Ensemble learning integrates multiple machine learning models to improve the overall prediction ability on limited data and hence alleviates the problem of overfitting effectively. Therefore, we apply the idea of ensemble learning to few-shot learning to improve the accuracy of few-shot classification. Metric learning is an important means to solve the problem of few-shot classification. In this paper, we propose ensemble-based deep metric learning (EBDM) for few-shot learning, which is trained end-to-end from scratch. We split the feature extraction network into two parts: the shared part and exclusive part. The shared part is the lower layers of the feature extraction network and is shared across ensemble members to reduce the number of parameters. The exclusive part is the higher layers of the feature extraction network and is exclusive to each individual learner. The coupling of the two parts naturally forces any diversity between the ensemble members to be concentrated on the deeper, unshared layers. We can obtain different features from the exclusive parts and then use these different features to compute diverse metrics. Combining these multiple metrics together will generate a more accurate ensemble metric. This ensemble metric can be used to assign labels to images of new classes with a higher accuracy. Our work leads to a simple, effective, and efficient framework for few-shot classification. The experimental results show that our approach attains superior performance, with the largest improvement of \(4.85\%\) in classification accuracy over related competitive baselines.
H. Lu—Also with MoE Key Lab of Articial Intelligence, AI Institute, Shanghai Jiao Tong University.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Andrychowicz, M., Denil, M.: learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems (2016)
Bertinetto, L.: Meta-learning with differentiable closed-form solvers. In: International Conference on Learning Representations (2019)
Cai, Q., Pan, Y., Yao, T., Yan: Memory matching networks for one-shot image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Finn, C., Abbeel, P.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70 (2017)
Finn, C., Xu, K.: Probabilistic model-agnostic meta-learning. In: Advances in Neural Information Processing Systems (2018)
Garcia, V.: Few-Shot Learning With Graph Neural Networks (2017)
Gidaris, S.: Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Ha, D., Dai, A.: Hypernetworks. arXiv preprint arXiv:1609.09106 (2016)
Hinton, G.: Deep neural networks for acoustic modeling in speech recognition. IEEE Sig. Process. Mag. 29, 82–97 (2012)
Jamal, M.A.: Task-agnostic meta-learning for few-shot learning. CoRR abs/1805.07722 (2018)
Kim, J., Kim, T.: Edge-labeling graph neural network for few-shot learning. CoRR abs/1905.01436 (2019)
Kim, T., Yoon: Bayesian model-agnostic meta-learning. arXiv preprint arXiv:1806.03836 (2018)
Koch, G., Zemel, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop (2015)
Li, H., Eigen, D.: Finding task-relevant features for few-shot learning by category traversal. CoRR abs/1905.11116 (2019)
Li, W., Wang, L.: Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)
Lifchitz, Y., Avrithis, Y.: Dense classification and implanting for few-shot learning. CoRR abs/1903.05050 (2019)
Munkhdalai, T., Yu, H.: Meta networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70 (2017)
Ravi, S., Larochelle, H.: Optimization as a Model for Few-shot Learning (2016)
Ren, M.: Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018)
Rusu, A.A., Rao, D.: Meta-learning with latent embedding optimization. arXiv preprint arXiv:1807.05960 (2018)
Santoro, A., Bartunov, S.: Meta-learning with memory-augmented neural networks. In: International Conference on Machine Learning (2016)
Snell, J., Swersky, K.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems (2017)
Sung, F., Yang, Y., Zhang, L.: Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Sung, F., Zhang, L.: Learning to learn: meta-critic networks for sample efficient learning. arXiv preprint arXiv:1706.09529 (2017)
Vinyals, O., Blundell, C.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems (2016)
Zhou, P., Yuan. X.: Efficient meta learning via minibatch proximal update. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Acknowledgement
This paper is supported by NSFC (No.61772330, 61533012, 61876109), the pre-research project (No.61403120201), Shanghai Key Laboratory of Crime Scene Evidence (2017XCWZK01) and the Interdisciplinary Program of Shanghai Jiao Tong University (YG2019QNA09).
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
Zhou, M., Li, Y., Lu, H. (2020). Ensemble-Based Deep Metric Learning for Few-Shot Learning. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-61609-0_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61608-3
Online ISBN: 978-3-030-61609-0
eBook Packages: Computer ScienceComputer Science (R0)