Skip to main content
SpringerLink
Log in

An Inverse Mapping with Manifold Alignment for Zero-Shot Learning

  • Conference paper
  • First Online:
MultiMedia Modeling (MMM 2020)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11962))

Included in the following conference series:

  • 2269 Accesses

Abstract

Zero-shot learning aims to recognize objects from unseen classes, where samples are not available at the training stage, by transferring knowledge from seen classes, where labeled samples are provided. It bridges seen and unseen classes via a shared semantic space such as class attribute space or class prototype space. While previous approaches have tried to learning a mapping function from the visual space to the semantic space with different objective functions, we take a different approach and try to map from the semantic space to the visual space. The inverse mapping predicts the visual feature prototype of each unseen class via the semantic vector for image classification. We also propose a heuristic algorithm to select a high density set from data of each seen class. The visual feature prototypes from the high density sets are more discriminative, which is benefit to the classification. Our approach is evaluated for zero-shot recognition on four benchmark data sets and significantly outperforms the state-of-the-art methods on AWA, SUN, APY.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  2. Larochelle, H., Erhan, D., Bengio, Y.: Zero-data learning of new tasks. In: AAAI, vol. 1, p. 3 (2008)

    Google Scholar 

  3. Guo, Y., Ding, G., Han, J., Tang, S.: Zero-shot learning with attribute selection. In: AAAI, pp. 6870–6877. AAAI Press (2018)

    Google Scholar 

  4. Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 4447–4456 (2017)

    Google Scholar 

  5. Norouzi, M., et al.: Zero-shot learning by convex combination of semantic embeddings. CoRR, vol. abs/1312.5650 (2013)

    Google Scholar 

  6. Shigeto, Y., Suzuki, I., Hara, K., Shimbo, M., Matsumoto, Y.: Ridge regression, hubness, and zero-shot learning. In: Appice, A., Rodrigues, P.P., Santos Costa, V., Soares, C., Gama, J., Jorge, A. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9284, pp. 135–151. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23528-8_9

    Chapter  Google Scholar 

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

    Article  Google Scholar 

  8. Li, Y., Wang, D., Hu, H., Lin, Y., Zhuang, Y.: Zero-shot recognition using dual visual-semantic mapping paths. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5207–5215 (2017)

    Google Scholar 

  9. Changpinyo, S., Chao, W.-L., Sha, F.: Predicting visual exemplars of unseen classes for zero-shot learning. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22–29 October 2017, pp. 3496–3505 (2017)

    Google Scholar 

  10. Frome, A., et al.: DeVISE: a deep visual-semantic embedding model. In: International Conference on Neural Information Processing Systems, pp. 2121–2129 (2013)

    Google Scholar 

  11. Akata, Z., Reed, S.E., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: CVPR, pp. 2927–2936. IEEE Computer Society (2015)

    Google Scholar 

  12. Xian, Y., Akata, Z., Sharma, G., Nguyen, Q., Hein, M., Schiele, B.: Latent embeddings for zero-shot classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 69–77 (2016)

    Google Scholar 

  13. Bucher, M., Herbin, S., Jurie, F.: Generating visual representations for zero-shot classification, pp. 2666–2673 (2017)

    Google Scholar 

  14. Jiang, H., Kim, B., Guan, M., Gupta, M.: To trust or not to trust a classifier. In: Advances in Neural Information Processing Systems, pp. 5542–5553 (2018)

    Google Scholar 

  15. Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning - the good, the bad and the ugly. In: CVPR, pp. 3077–3086. IEEE Computer Society (2017)

    Google Scholar 

  16. Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453–465 (2014)

    Article  Google Scholar 

  17. Socher, R., Ganjoo, M., Manning, C.D., Ng, A.Y.: Zero-shot learning through cross-modal transfer. In: NIPS, pp. 935–943 (2013)

    Google Scholar 

  18. Zhang, Z., Saligrama, V.: Zero-shot recognition via structured prediction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 533–548. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_33

    Chapter  Google Scholar 

  19. Xian, Y., Akata, Z., Sharma, G., Nguyen, Q.N., Hein, M., Schiele, B.: Latent embeddings for zero-shot classification. CoRR, vol. abs/1603.08895 (2016)

    Google Scholar 

  20. Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label embedding for image classication. IEEE Trans. Pattern Anal. Mach. Intell. 38(7), 1425–1438 (2016)

    Article  Google Scholar 

  21. Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: International Conference on Machine Learning, pp. 2152–2161 (2015)

    Google Scholar 

  22. Morgado, P., Vasconcelos, N.: Semantically consistent regularization for zero-shot recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 2037–2046 (2017)

    Google Scholar 

  23. Verma, V.K., Rai, P.: A simple exponential family framework for zero shot learning. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10535, pp. 792–808. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71246-8_48

    Chapter  Google Scholar 

  24. Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer (2009)

    Google Scholar 

  25. Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 1778–1785. IEEE (2009)

    Google Scholar 

  26. Socher, R., Ganjoo, M., Sridhar, H., Bastani, O., Manning, C.D., Ng, A.Y.: Zero-shot learning through cross-modal transfer. In: International Conference on Neural Information Processing Systems (2013)

    Google Scholar 

  27. Elhoseiny, M.: Write a classifier: zero shot learning using purely textual descriptions. In: IEEE International Conference on Computer Vision (2014)

    Google Scholar 

  28. Lei Ba, J., Swersky, K., Fidler, S., Salakhutdinov, R.: Predicting deep zero-shot convolutional neural networks using textual descriptions (2015)

    Google Scholar 

Download references

Acknowledgment

This work is supported by NSFC project Grant No. U18331 01, Shenzhen Science and Technologies project under Grant No. JCYJ201604281 82137473 and the Joint Research Center of Tencent and Tsinghua.

Author information

Authors and Affiliations

  1. Computer Science and Technology, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China

    Xixun Wu, Binheng Song, Zhixiang Wang & Chun Yuan

  2. Peng Cheng Laboratory, Shenzhen, China

    Chun Yuan

Authors
  1. Xixun Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Binheng Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhixiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chun Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Xixun Wu , Binheng Song , Zhixiang Wang or Chun Yuan .

Editor information

Editors and Affiliations

  1. Korea Advanced Institute of Science and Technology, Daejeon, Korea (Republic of)

    Yong Man Ro

  2. National Chiao Tung University, Hsinchu, Taiwan

    Wen-Huang Cheng

  3. Korea Advanced Institute of Science and Technology, Daejeon, Korea (Republic of)

    Junmo Kim

  4. National Cheng Kung University, Tainan City, Taiwan

    Wei-Ta Chu

  5. Tsinghua University, Beijing, China

    Peng Cui

  6. Korea Advanced Institute of Science and Technology, Daejeon, Korea (Republic of)

    Jung-Woo Choi

  7. National Tsing Hua University, Hsinchu, Taiwan

    Min-Chun Hu

  8. Ghent University, Ghent, Belgium

    Wesley De Neve

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wu, X., Song, B., Wang, Z., Yuan, C. (2020). An Inverse Mapping with Manifold Alignment for Zero-Shot Learning. In: Ro, Y., et al. MultiMedia Modeling. MMM 2020. Lecture Notes in Computer Science(), vol 11962. Springer, Cham. https://doi.org/10.1007/978-3-030-37734-2_33

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-37734-2_33

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-37733-5

  • Online ISBN: 978-3-030-37734-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation