Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.5555/3237383.3238056acmconferencesArticle/Chapter ViewAbstractPublication PagesaamasConference Proceedingsconference-collections
research-article

One-Shot Learning using Mixture of Variational Autoencoders: a Generalization Learning approach

Published: 09 July 2018 Publication History

Abstract

Deep learning, even if it is very successful nowadays, traditionally needs very large amounts of labeled data to perform excellent on the classification task. In an attempt to solve this problem, the one-shot learning paradigm, which makes use of just one labeled sample per class and prior knowledge, becomes increasingly important. In this paper, we propose a new one-shot learning method, dubbed MoVAE (Mixture of Variational AutoEncoders), to perform classification. Complementary to prior studies, MoVAE represents a shift of paradigm in comparison with the usual one-shot learning methods, as it does not use any prior knowledge. Instead, it starts from zero knowledge and one labeled sample per class. Afterward, by using unlabeled data and the generalization learning concept (in a way, more as humans do), it is capable to gradually improve by itself its performance. Even more, if there are no unlabeled data available MoVAE can still perform well in one-shot learning classification. We demonstrate empirically the efficiency of our proposed approach on three datasets, i.e. the handwritten digits (MNIST), fashion products (Fashion-MNIST), and handwritten characters (Omniglot), showing that MoVAE outperforms state-of-the-art one-shot learning algorithms.

References

[1]
P. Agrawal, J. Carreira, and J. Malik . 2015. Learning to See by Moving. In 2015 IEEE International Conference on Computer Vision (ICCV). 37--45.
[2]
Franccois Chollet . 2015. keras. https://github.com/fchollet/keras. (2015).
[3]
N. Dalal and B. Triggs . 2005. Histograms of oriented gradients for human detection 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), Vol. Vol. 1. 886--893 vol. 1.
[4]
Mark A. Gluck, Eduardo Mercado, and Catherine E. Myers . 2011. Learning and Memory: From Brain to Behavior (bibinfoedition2nd ed.). New York: Worth Publishers.
[5]
Yuval Noah Harari . 2015. Sapiens: A Brief History of Humankind.
[6]
D. P. Kingma and M. Welling . 2013. Auto-encoding variational Bayes. CoRR Vol. arXiv:1312.6114 (2013).
[7]
Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov . 2015. Siamese Neural Networks for One-shot Image Recognition.
[8]
Brenden M. Lake, Ruslan Salakhutdinov, and Joshua B. Tenenbaum . 2015. Human-level concept learning through probabilistic program induction. Science, Vol. 350, 6266 (11 Dec. . 2015), 1332--1338.
[9]
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner . 1998. Gradient-Based Learning Applied to Document Recognition Proceedings of the IEEE, Vol. Vol. 86. 2278--2324.
[10]
Geert J. S. Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A. W. M. van der Laak, Bram van Ginneken, and Clara I. Sánchez . 2017. A Survey on Deep Learning in Medical Image Analysis. CoRR Vol. abs/1702.05747 (2017). http://arxiv.org/abs/1702.05747
[11]
Patricio Loncomilla, Javier Ruiz del Solar, and Luz Martínez . 2016. Object recognition using local invariant features for robotic applications: A survey. Pattern Recognition Vol. 60 (2016), 499 -- 514.
[12]
W. Ouyang, X. Wang, X. Zeng, Shi Qiu, P. Luo, Y. Tian, H. Li, Shuo Yang, Zhe Wang, Chen-Change Loy, and X. Tang . 2015. DeepID-Net: Deformable deep convolutional neural networks for object detection 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2403--2412.
[13]
J. Thewlis, H. Bilen, and A. Vedaldi . 2017. Unsupervised object learning from dense invariant image labelling Proceedings of Advances in Neural Information Processing Systems (NIPS).
[14]
Oriol Vinyals, Charles Blundell, Timothy P. Lillicrap, Koray Kavukcuoglu, and Daan Wierstra . 2016. Matching Networks for One Shot Learning. (2016), 3630--3638.
[15]
D.A. Waterman . 1970. Generalization learning techniques for automating the learning of heuristics. Artificial Intelligence Vol. 1, 1 (1970), 121 -- 170.
[16]
Alex Wong and Alan L Yuille . 2015. One shot learning via compositions of meaningful patches Proceedings of the IEEE International Conference on Computer Vision. 1197--1205.
[17]
Han Xiao, Kashif Rasul, and Roland Vollgraf . 2017. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. (2017).

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems
July 2018
2312 pages

Sponsors

In-Cooperation

Publisher

International Foundation for Autonomous Agents and Multiagent Systems

Richland, SC

Publication History

Published: 09 July 2018

Check for updates

Author Tags

  1. collective intelligence
  2. generalization learning
  3. one-shot learning
  4. semi-supervised learning
  5. variational autoencoders

Qualifiers

  • Research-article

Conference

AAMAS '18
Sponsor:
AAMAS '18: Autonomous Agents and MultiAgent Systems
July 10 - 15, 2018
Stockholm, Sweden

Acceptance Rates

AAMAS '18 Paper Acceptance Rate 149 of 607 submissions, 25%;
Overall Acceptance Rate 1,155 of 5,036 submissions, 23%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 98
    Total Downloads
  • Downloads (Last 12 months)3
  • Downloads (Last 6 weeks)0
Reflects downloads up to 11 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media