Skip to main content

2019 | OriginalPaper | Buchkapitel

Attention Relational Network for Few-Shot Learning

verfasst von : Jia Shuai, JiaMing Chen, Meng Yang

Erschienen in: Intelligence Science and Big Data Engineering. Big Data and Machine Learning

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Few-shot learning aims to learn a model which can quickly generalize with only a small number of labeled samples per class. The situation we consider is how to use the information of the test set to generate the better prototype representation of the training set. In this paper, based on attention mechanism we propose a flexible and efficient framework for few-shot feature fusion, called Attention Relational Network (ARN) which is a three-branch structure of embedding module, weight module and matching module. Specifically, with attention mechanism, the proposed ARN can model adaptively the constribution weights of sample features from embedding module and then generate the prototype representations by weighted fusion of the sample features. Finally, the matching module identify target sample by calculating the matching scores. We evaluated this method on the MiniImageNet and Omniglot dataset, and the experiment proved that our method is very attractive.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Ba, J., Mnih, V.K.: Multiple object recognition with visual attention (2015) Ba, J., Mnih, V.K.: Multiple object recognition with visual attention (2015)
2.
Zurück zum Zitat Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation, pp. 3640–3649. IEEE (2016) Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation, pp. 3640–3649. IEEE (2016)
3.
Zurück zum Zitat Edwards, H., Storkey, A.: Towards a neural statistician (2017) Edwards, H., Storkey, A.: Towards a neural statistician (2017)
4.
Zurück zum Zitat Feng, W., Tax, D.M.J.: Survey on the attention based RNN model and its applications in computer vision (2016) Feng, W., Tax, D.M.J.: Survey on the attention based RNN model and its applications in computer vision (2016)
5.
Zurück zum Zitat Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks (2017) Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks (2017)
7.
Zurück zum Zitat Fu, J., Liu, J., Tian, H., Fang, Z., Lu, H.: Dual attention network for scene segmentation (2018) Fu, J., Liu, J., Tian, H., Fang, Z., Lu, H.: Dual attention network for scene segmentation (2018)
8.
Zurück zum Zitat Garcia, V., Bruna, J.: Few-shot learning with graph neural networks (2017) Garcia, V., Bruna, J.: Few-shot learning with graph neural networks (2017)
9.
Zurück zum Zitat Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. Comput. Sci., 1462–1471 (2015) Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. Comput. Sci., 1462–1471 (2015)
10.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
11.
Zurück zum Zitat Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks (2017) Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks (2017)
12.
Zurück zum Zitat Kaiser, Ł., Nachum, O., Roy, A., Bengio, S.: Learning to remember rare events (2016) Kaiser, Ł., Nachum, O., Roy, A., Bengio, S.: Learning to remember rare events (2016)
13.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks (2017) Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks (2017)
14.
Zurück zum Zitat Lake, B., Salakhutdinov, R., Gross, J., Tenenbaum, J.: One shot learning of simple visual concepts. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society, January 2011 Lake, B., Salakhutdinov, R., Gross, J., Tenenbaum, J.: One shot learning of simple visual concepts. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society, January 2011
15.
Zurück zum Zitat Larochelle, S.R.H.: Optimization as a model for few-shot learning (2017) Larochelle, S.R.H.: Optimization as a model for few-shot learning (2017)
16.
Zurück zum Zitat Li, F.F., Rob, F., Pietro, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)CrossRef Li, F.F., Rob, F., Pietro, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)CrossRef
17.
Zurück zum Zitat Mishra, N., Rohaninejad, M., Xi, C., Abbeel, P.: Meta-learning with temporal convolutions (2017) Mishra, N., Rohaninejad, M., Xi, C., Abbeel, P.: Meta-learning with temporal convolutions (2017)
18.
Zurück zum Zitat Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention, vol. 3 (2014) Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention, vol. 3 (2014)
19.
Zurück zum Zitat Salakhutdinov, G.K.Z.: Siamese neural networks for one-shot image recognition. In: International Conference on Machine Learning (2015) Salakhutdinov, G.K.Z.: Siamese neural networks for one-shot image recognition. In: International Conference on Machine Learning (2015)
20.
Zurück zum Zitat Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33rd International Conference on Machine Learning, Proceedings of Machine Learning Research, 20–22 June 2016, vol. 48, pp. 1842–1850. PMLR, New York (2016) Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33rd International Conference on Machine Learning, Proceedings of Machine Learning Research, 20–22 June 2016, vol. 48, pp. 1842–1850. PMLR, New York (2016)
21.
Zurück zum Zitat Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014) Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:​1409.​1556 (2014)
22.
Zurück zum Zitat Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning (2017) Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning (2017)
23.
Zurück zum Zitat Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning (2018) Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning (2018)
24.
Zurück zum Zitat Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning (2016) Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning (2016)
25.
Zurück zum Zitat Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module (2018) Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module (2018)
26.
Zurück zum Zitat Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. Comput. Sci., 2048–2057 (2015) Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. Comput. Sci., 2048–2057 (2015)
27.
Zurück zum Zitat Yang, D., Yuan, C., Bing, L., Zhao, L., Hu, W.: Interaction-aware spatio-temporal pyramid attention networks for action classification (2018) Yang, D., Yuan, C., Bing, L., Zhao, L., Hu, W.: Interaction-aware spatio-temporal pyramid attention networks for action classification (2018)
Metadaten
Titel
Attention Relational Network for Few-Shot Learning
verfasst von
Jia Shuai
JiaMing Chen
Meng Yang
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-36204-1_13