Advertisement

From Classical to Generalized Zero-Shot Learning: A Simple Adaptation Process

  • Yannick Le CacheuxEmail author
  • Hervé Le Borgne
  • Michel Crucianu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11296)

Abstract

Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes. It relies on additional semantic knowledge for which a mapping can be learned with training examples of seen classes. While classical ZSL considers the recognition performance on unseen classes only, generalized zero-shot learning (GZSL) aims at maximizing performance on both seen and unseen classes. In this paper, we propose a new process for training and evaluation in the GZSL setting; this process addresses the gap in performance between samples from unseen and seen classes by penalizing the latter, and enables to select hyper-parameters well-suited to the GZSL task. It can be applied to any existing ZSL approach and leads to a significant performance boost: the experimental evaluation shows that GZSL performance, averaged over eight state-of-the-art methods, is improved from 28.5 to 42.2 on CUB and from 28.2 to 57.1 on AwA2.

Keywords

Zero-shot learning Multimodal classification 

References

  1. 1.
    Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(7), 1425–1438 (2016)CrossRefGoogle Scholar
  2. 2.
    Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the CVPR 2015, pp. 2927–2936. IEEE (2015)Google Scholar
  3. 3.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)zbMATHGoogle Scholar
  4. 4.
    Bucher, M., Herbin, S., Jurie, F.: Generating visual representations for zero-shot classification. In: ICCV Workshops: TASK-CV. IEEE (2017)Google Scholar
  5. 5.
    Changpinyo, S., Chao, W.L., Gong, B., Sha, F.: Synthesized classifiers for zero-shot learning. In: Proceedings of the CVPR 2016, pp. 5327–5336. IEEE (2016)Google Scholar
  6. 6.
    Chao, W.-L., Changpinyo, S., Gong, B., Sha, F.: An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 52–68. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_4CrossRefGoogle Scholar
  7. 7.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the CVPR 2009, pp. 248–255. IEEE (2009)Google Scholar
  8. 8.
    Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Proceedings of the NIPS 2013, pp. 2121–2129 (2013)Google Scholar
  9. 9.
    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)CrossRefGoogle Scholar
  10. 10.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR 2016, pp. 770–778. IEEE (2016)Google Scholar
  11. 11.
    Kodirov, E., Xiang, T., Fu, Z., Gong, S.: Unsupervised domain adaptation for zero-shot learning. In: Proceedings of the CVPR 2015, pp. 2452–2460. IEEE (2015)Google Scholar
  12. 12.
    Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: Proceedings of the CVPR 2017, pp. 4447–4456. IEEE (2017)Google Scholar
  13. 13.
    Kumar Verma, V., Arora, G., Mishra, A., Rai, P.: Generalized zero-shot learning via synthesized examples. In: Proceedings of the CVPR 2010, pp. 4281–4289. IEEE (2018)Google Scholar
  14. 14.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: Proceedings of the CVPR 2009, pp. 951–958. IEEE (2009)Google Scholar
  15. 15.
    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)CrossRefGoogle Scholar
  16. 16.
    Larochelle, H., Erhan, D., Bengio, Y.: Zero-data learning of new tasks. In: AAAI, vol. 1, p. 3 (2008)Google Scholar
  17. 17.
    Palatucci, M., Pomerleau, D., Hinton, G.E., Mitchell, T.M.: Zero-shot learning with semantic output codes. In: Proceedings of the NIPS 2009, pp. 1410–1418 (2009)Google Scholar
  18. 18.
    Radovanović, M., Nanopoulos, A., Ivanović, M.: Hubs in space: popular nearest neighbors in high-dimensional data. J. Mach. Learn. Res. 11, 2487–2531 (2010)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Rohrbach, M., Ebert, S., Schiele, B.: Transfer learning in a transductive setting. In: Proceedings of the NIPS 2013, pp. 46–54 (2013)Google Scholar
  20. 20.
    Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: Proceedings of the ICML 2015, pp. 2152–2161 (2015)Google Scholar
  21. 21.
    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_9CrossRefGoogle Scholar
  22. 22.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the CVPR 2015, pp. 1–9. IEEE (2015)Google Scholar
  23. 23.
    Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)Google Scholar
  24. 24.
    van Wieringen, W.N.: Lecture notes on ridge regression. arXiv preprint arXiv:1509.09169 (2015)
  25. 25.
    Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly. arXiv preprint arXiv:1707.00600 (2017)
  26. 26.
    Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the CVPR 2018. IEEE (2018)Google Scholar
  27. 27.
    Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning - the good, the bad and the ugly. In: Proceedings of the CVPR 2017, pp. 3077–3086. IEEE (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yannick Le Cacheux
    • 1
    Email author
  • Hervé Le Borgne
    • 1
  • Michel Crucianu
    • 2
  1. 1.CEA LISTGif-sur-YvetteFrance
  2. 2.CEDRIC – CNAMParisFrance

Personalised recommendations