Skip to main content
SpringerLink
Log in

Discriminant Zero-Shot Learning with Center Loss

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Current work on zero-shot learning (ZSL) generally does not focus on the discriminative ability of the models, which is important for differentiating between classes since our brain focuses on the discriminating part of the object to classify it. For generalized ZSL (GZSL), the fact that the outputs of the model are not comparable leads to a degraded performance. We propose a new ZSL method with a center loss to make the instances from the same class more compact by extracting their discriminative parts. Further, we introduce a varying learning rate to accelerate the model selection process. We also demonstrate how to boost the performance of GZSL by rectifying the outputs of the model to make the outputs be comparable. Experimental results on four benchmarks, including SUN, CUB, AWA2, and aPY, demonstrate the superiority of the proposed method, therein achieving state-of-the-art performance.

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

Access this article

Log in via an institution

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

References

  1. Akata Z, Perronnin F, Harchaoui Z, Schmid C. 2013. Label-Embedding for attribute-based classification. In: 2013 IEEE Conference on computer vision and pattern recognition, p. 819–826.

  2. Akata Z, Perronnin F, Harchaoui Z, Schmid C. Label-Embedding for image classification. IEEE Trans Pattern Anal Mach Intell 2016;38(7):1425–38.

    Article  PubMed  Google Scholar 

  3. Akata Z, Reed S, Walter D, Lee H, Schiele B. 2015. Evaluation of output embeddings for fine-grained image classification. In: CVPR 2016, p. 2927–2936.

  4. Ba JL, Swersky K, Fidler S, Salakhutdinov R. 2015. Predicting deep zero-shot convolutional neural networks using textual descriptions. In: ICCV 2015. p. 4247–4255.

  5. Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res 2012;13:281–305.

    Google Scholar 

  6. Bucher M, Herbin S, Jurie F. 2016. Improving semantic embedding consistency by metric learning for zero-Shot classiffication. In: ECCV 2016, Lecture Notes in Computer Science. Springer International Publishing, p. 730–746.

  7. Changpinyo S, Chao W-L, Gong B, Sha F. 2016. Synthesized Classifiers for Zero-Shot. Learning, p. 5327–5336.

  8. Changpinyo S, Chao W-L, Sha F. 2016. Predicting visual exemplars of unseen classes for zero-Shot learning. In: ICCV 2017.

  9. Chao W-L, Changpinyo S, Gong B, Sha F. 2016. An empirical study and analysis of generalized zero-Shot learning for object recognition in the wild. In: ECCV 2016.

  10. Frome A, Corrado GS, Shlens J, Bengio S, Dean J, Marc’Aurelio R, Mikolov T. 2013. DeviSE A Deep visual-Semantic Embedding Model. In: Advances in neural information processing systems 26, p. 2121–2129.

  11. Jayaraman D, Grauman K. 2014. Zero-shot recognition with unreliable attributes. In: Advances in neural information processing systems, p. 3464–3472.

  12. Jiang H, Wang R, Shan S, Yang Y, Chen X. 2017. Learning discriminative latent attributes for zero-Shot classification. In: 2017 IEEE international conference on computer vision (ICCV), p. 4233–4242.

  13. Jin X-B, Geng G-G, Xie G-S, Huang K. Approximately optimizing NDCG using pair-wise loss. Inf Sci 2018;453:50–65.

    Article  Google Scholar 

  14. Jin X-B, Xie G-S, Huang K, Hussain A. 2018. Accelerating infinite ensemble of clustering by pivot features. Cognitive Computation, p. 1–9.

  15. Jin X-B, Zhang X-Y, Huang K, Geng G-G. 2017. Stochastic Conjugate Gradient Algorithm with Variance Reduction. arXiv:1710.09979.

  16. Kodirov E, Xiang T, Gong S. 2017. Semantic autoencoder for zero-Shot learning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), p. 4447–4456.

  17. Kodirov E, Xiang T, Fu Z, Gong S. 2015. Unsupervised domain adaptation for zero-Shot learning. In: ICCV 2015, p. 2452–2460.

  18. Lampert CH, Nickisch H, Harmeling S. Attribute-based classification for zero-Shot visual object categorization. IEEE Trans Pattern Anal Mach Intell 2014;36(3):453– 65.

    Article  PubMed  Google Scholar 

  19. Lampert CH, Nickisch H, Harmeling S. 2009. Learning to detect unseen object classes by between-class attribute transfer. In: 2009. CVPR 2009. IEEE conference on Computer vision and pattern recognition. IEEE, p. 951–958.

  20. Li Y, Zhang J, Xhang J, Huang K. 2018. Discriminative learning of latent features for zero-Shot recognition.

  21. Loshchilov I, Hutter F. 2017. SGDR Stochastic gradient descent with warm restarts. In: ICLR 2017.

  22. Norouzi M, Mikolov T, Bengio S, Singer Y, Shlens J, Frome A, Corrado GS, Jeffrey D. 2013. Zero-Shot learning by convex combination of semantic embeddings. In: ICLR 2014.

  23. Palatucci M, Pomerleau D, Hinton GE, Mitchell TM. Zero-shot Learning with Semantic Output Codes. Advances in Neural Information Processing Systems. In: Bengio Y, Schuurmans D, Lafferty JD, Williams CKI, and Culotta A, editors; 2009. p. 1410– 1418.

  24. Peng P, Tian Y, Xiang T, Wang Y, Huang T. 2016. Joint learning of semantic and latent attributes. In: European conference on computer vision. Springer. p. 336–353.

  25. Romera-Paredes B, Torr PHS. 2015. An Embarrassingly Simple Approach to Zero-shot Learning. In: ICML, ICML’15, Lille, p. 2152–2161. JMLR.org.

  26. Scheirer WJ, de Rezende Rocha A, Sapkota A, Boult TE. Toward open set recognition. IEEE Trans Pattern Anal Mach Intell 2013;35(7):1757–72.

    Article  PubMed  Google Scholar 

  27. Shigeto Y, Suzuki I, Hara K, Shimbo M, Matsumoto Y. Ridge Regression, Hubness, and Zero-Shot Learning. ECML PKDD 2015, Lecture Notes in Computer Science. In: Appice A, Rodrigues PP, Costa VS, Soares C, Gama J, and Jorge A, editors. Springer; 2015. p. 135–151.

  28. Socher R, Ganjoo M, Manning CD, Ng AY. 2013. Zero-shot learning through cross-modal transfer. In: Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1, NIPS’13, p. 935–943, USA.

  29. Spratling MW. A hierarchical predictive coding model of object recognition in natural images. Cogn Comput 2017;9(2):151– 67.

    Article  CAS  Google Scholar 

  30. Wen Y, Zhang K, Li Z, Qiao Y. A discriminative feature learning approach for deep face recognition. Computer Vision – ECCV Lecture Notes in Computer Science. In: Leibe, B, Matas, J, Sebe, N, and Welling, M, editors. Springer International Publishing; 2016. p. 2016.

  31. Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B. 2016. Latent Embeddings for Zero-shot Classification. In: CVPR 2016.

  32. Xian Y, Schiele B, Akata Z. 2017. Zero-Shot Learning - The Good, the Bad and the Ugly. In: CVPR 2017, arXiv:1703.04394.

  33. Xie J, Yu L, Zhu L, Chen X. Semantic image segmentation method with multiple adjacency trees and multiscale features. Cogn Comput 2017;9(2):168–79.

    Article  Google Scholar 

  34. Yang FSY, Zhang L, Xiang T, Torr PHS, Hospedales TM. 2018. Learning to compare: Relation network for few-shot learning.

  35. Zhang L, Xiang T, Gong S. 2017. Learning a deep embedding model for zero-Shot learning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), p. 3010–3019.

  36. Zhang Z, Saligrama V. 2015. Zero-Shot learning via semantic similarity embedding. In: ICCV 2015. p. 4166–4174.

  37. Zhang Ziming, Saligrama V. 2016. Zero-Shot Learning via Joint Latent Similarity Embedding, p. 6034–6042.

  38. Zhong G, Zheng Y, Zhang X-Y, Wei H, Ling X. 2018. Convolutional discriminant analysis. In: ICPR 2018, p. 6.

Download references

Funding

This work was partially supported by the Fundamental Research Funds for the Henan Provincial Colleges and Universities in the Henan University of Technology (2016RCJH06), the National Natural Science Foundation of China (61103138, U1804159, 61702163 and 61602154), Natural Science Foundation of the Jiangsu Higher Education Institutions of China (17KJB520041,KSF-A-10).

Author information

Authors and Affiliations

  1. Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China

    Xiao-Bo Jin, Kaizhu Huang & Qiu-Feng Wang

  2. College of Information Science and Engineering, Henan University of Science and Technology, Luoyang, China

    Guo-Sen Xie

  3. College of Information Science and Engineering, Henan University of Technology, Zhengzhou, China

    Heling Cao

Authors
  1. Xiao-Bo Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guo-Sen Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kaizhu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Heling Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qiu-Feng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiao-Bo Jin.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants performed by any of the authors.

Informed Consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher’s Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jin, XB., Xie, GS., Huang, K. et al. Discriminant Zero-Shot Learning with Center Loss. Cogn Comput 11, 503–512 (2019). https://doi.org/10.1007/s12559-019-09629-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-019-09629-z

Keywords

Search

Navigation