Skip to main content

Advertisement

Springer Nature Link
Log in

Zero-shot learning via self-organizing maps

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Collecting-labeled images from all possible classes related to the task at hand is highly impractical and may even be impossible. At this point, Zero-Shot Learning (ZSL) can enable the classification of new test classes for which there are no labeled images for training. The vast majority of existing ZSL methods aim to learn a projection from the feature space into the semantic space, where all classes are represented by a list of semantic attributes. To this end, they usually try to solve a complex optimization problem. Nevertheless, the semantic features (attributes) may not be suitable to represent the images because they are derived based on human knowledge and are, therefore, abstract. Alternatively, in this study, we introduce a novel ZSL method called SOMZSL, which has its roots in Self-Organizing Maps (SOM), a famous data visualization method. In particular, SOMZSL builds two SOMs of the same size and shape, one for the feature space and one for the attribute space, and then establishes a correspondence between them. Instead of considering a direct projection between the feature space and the attribute space, which is inherently different, SOMZSL connects them through comparable intermediate layers, i.e., SOMs. In terms of performance, SOMZSL can classify novel test classes as well or even better than existing ZSL methods without dealing with a complex optimization problem, thanks to the heuristic nature of SOM on which it is based. Finally, SOMZSL uses unlabeled test images in the construction of SOMs and can thus mitigate the domain shift problem inherent in ZSL.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availibility statement

The data used in this research are public and can be accessed through the references provided.

References

  1. Palatucci MM, Pomerleau DA, Hinton GE, Mitchell T (2009) Zero-shot learning with semantic output codes. In: Proceedings of advances in neural information processing systems, 22

  2. Lampert CH, Nickisch H, Harmeling S (2013) Attribute-based classification for zero-shot visual object categorization. IEEE Transact Pattern Anal Mach Intell 36(3):453–465

    Article  Google Scholar 

  3. Xian Y, Lampert CH, Schiele B, Akata Z (2018) Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly. IEEE Transact Pattern Anal Mach Intell 41(9):2251–2265

    Article  Google Scholar 

  4. Lampert, C.H., Nickisch, H., Harmeling, S (2009) Learning to detect unseen object classes by between-class attribute transfer. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 951–958 . IEEE

  5. Akata Z, Perronnin F, Harchaoui Z, Schmid C (2015) Label-embedding for image classification. IEEE Transact Pattern Anal Mach Intell 38(7):1425–1438

    Article  Google Scholar 

  6. Kodirov E, Xiang T, Gong S (2017) Semantic autoencoder for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 3174–3183

  7. Frome A, Corrado GS, Shlens J, Bengio S, Dean J, Ranzato MA, Mikolov T (2013) Devise: a deep visual-semantic embedding model. In: Proceedings of advances in neural information processing systems, 26

  8. Akata Z, Reed S, Walter D, Lee H, Schiele B (2015) Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2927–2936

  9. Romera-Paredes B, Torr P (2015) An embarrassingly simple approach to zero-shot learning. In: Proceedings of international conference on machine learning, pp 2152–2161. PMLR

  10. Li K, Min MR, Fu Y (2019) Rethinking zero-shot learning: A conditional visual classification perspective. In: Proceedings of the IEEE/CVF international conference on computer vision, p 3583–3592

  11. Fu Y, Hospedales TM, Xiang T, Gong S (2015) Transductive multi-view zero-shot learning. IEEE Transact Pattern Anal Mach Intell 37(11):2332–2345

    Article  Google Scholar 

  12. Kohonen T (2000) Self-Organizing Maps. Springer, Berlin

    MATH  Google Scholar 

  13. Chen Z, Liu B (2018) Lifelong machine learning. Synth Lect Artif Intell Mach Learn 12(3):1–207

    Google Scholar 

  14. Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Transact Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  15. Sariyildiz MB, Cinbis RG (2019) Gradient matching generative networks for zero-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, p 2168–2178

  16. Annadani Y, Biswas S (2018) Preserving semantic relations for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 7603–7612

  17. Changpinyo S, Chao WL, Gong B, Sha F (2016) Synthesized classifiers for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 5327–5336

  18. Liu S, Long M, Wang J, Jordan MI (2018) Generalized zero-shot learning with deep calibration network, 31

  19. Lei Ba J, Swersky K, Fidler S (2015) Predicting deep zero-shot convolutional neural networks using textual descriptions. In: Proceedings of the IEEE international conference on computer vision, p 4247–4255

  20. Zhang L, Wang P, Liu L, Shen C, Wei W, Zhang Y, Van Den Hengel A (2020) Towards effective deep embedding for zero-shot learning. IEEE Transact Circuits Syst Video Technol 30(9):2843–2852

    Article  Google Scholar 

  21. Mishra A, Krishna Reddy S, Mittal A, Murthy HA(2018) A generative model for zero shot learning using conditional variational autoencoders. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, p 2188–2196

  22. Chalasani R, Principe JC (2015) Self-organizing maps with information theoretic learning. Neurocomputing 147:3–14

    Article  Google Scholar 

  23. Laerhoven, K.V (2001) Combining the self-organizing map and k-means clustering for on-line classification of sensor data. In: Proceedings of the international conference on artificial neural networks, p 464–469

  24. Liu Y, Weisberg RH (2011) A review of self-organizing map applications in meteorology and oceanography. Self-Organ Maps: Appl Novel Algorithm Des 1:253–272

    Google Scholar 

  25. Alahakoon D, Halgamuge SK (2000) Dynamic self-organizing maps with controlled growth for knowledge discovery. IEEE Transact Neural Netw 11:601–614

    Article  Google Scholar 

  26. Akinduko AA, Mirkes EM, Gorban AN (2016) Som: Stochastic initialization versus principal components. Inform Sci 364:213–221

    Article  Google Scholar 

  27. Cottrell M, Olteanu M, Rossi F, Villa-Vialaneix N (2018) Self-organizing maps, theory and applications. Revista de Investigacion Operacional 39(1):1–22

    MathSciNet  MATH  Google Scholar 

  28. Mariette J, Villa-Vialaneix N (2016) Aggregating self-organizing maps with topology preservation. Adv Self-Organ Maps Learn Vector Quant. Springer, Berlin, pp 27–37

    Chapter  Google Scholar 

  29. Bourgeois N, Cottrell M, Déruelle B, Lamassé S, Letrémy P (2015) How to improve robustness in kohonen maps and display additional information in factorial analysis: application to text mining. Neurocomputing 147:120–135

    Article  Google Scholar 

  30. Zheng L, Yang Y, Tian Q (2017) Sift meets cnn: a decade survey of instance retrieval. IEEE Transact Pattern Anal Mach Intell 40(5):1224–1244

    Article  Google Scholar 

  31. Patterson G, Hays J (2012) Sun attribute database: Discovering, annotating, and recognizing scene attributes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 2751–2758

  32. Farhadi A, Endres I, Hoiem D, Forsyth D (2009) Describing objects by their attributes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 1778–1785

  33. Welinder P, Branson S, Mita T, Wah C, Schroff F, Belongie S, Perona P (2010) Caltech-ucsd birds 200

  34. Van Horn G, Branson S, Farrell R, Haber S, Barry J, Ipeirotis P, Perona P, Belongie S (2015) Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 595–604

  35. Elhoseiny M, Elfeki M (2019) Creativity inspired zero-shot learning. In: Proceedings of the IEEE/CVF international conference on computer vision, p 5784–5793

  36. Kohonen T (2013) Essentials of the self-organizing map. Neural Netw 37:52–65

    Article  Google Scholar 

  37. Cottrell M, Olteanu M, Rossi F, Villa-Vialaneix N (2016) Theoretical and applied aspects of the self-organizing maps. Adv Self-Org Maps Learn Vector Quant. Springer, Berlin, pp 3–26

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Sivas Cumhuriyet University, 58140, Sivas, Turkey

    Firat Ismailoglu

Authors
  1. Firat Ismailoglu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Firat Ismailoglu.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ismailoglu, F. Zero-shot learning via self-organizing maps. Neural Comput & Applic 35, 9931–9945 (2023). https://doi.org/10.1007/s00521-023-08299-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08299-1

Keywords