Advertisement

Model Selection for Generalized Zero-Shot Learning

  • Hongguang ZhangEmail author
  • Piotr Koniusz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11130)

Abstract

In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which makes it hard for the classifier to distinguish if a given testing sample comes from a seen or unseen class. However, using Generative Adversarial Network (GAN) to generate auxiliary datapoints by the semantic embeddings of unseen classes alleviates the above problem. Current approaches combine the auxiliary datapoints and original training data to train the generalized zero-shot learning model and obtain state-of-the-art results. Inspired by such models, we propose to feed the generated data via a model selection mechanism. Specifically, we leverage two sources of datapoints (observed and auxiliary) to train some classifier to recognize which test datapoints come from seen and which from unseen classes. This way, generalized zero-shot learning can be divided into two disjoint classification tasks, thus reducing the negative influence of the unbalanced data distribution. Our evaluations on four publicly available datasets for generalized zero-shot learning show that our model obtains state-of-the-art results.

Keywords

Model selection Generalized zero-shot learning Generative Adversarial Network 

References

  1. 1.
    Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: CVPR (2018)Google Scholar
  2. 2.
    Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for attribute-based classification. In: CVPR, pp. 819–826 (2013)Google Scholar
  3. 3.
    Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: ICML, pp. 2152–2161 (2015)Google Scholar
  4. 4.
    Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: CVPR, pp. 2927–2936 (2015)Google Scholar
  5. 5.
    Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning - the good, the bad and the ugly. In: CVPR (2017)Google Scholar
  6. 6.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Zhang, H., Koniusz, P.: Zero-shot kernel learning. In: CVPR, pp. 7670–7679 (2018)Google Scholar
  8. 8.
    Zhang, H., Koniusz, P.: Power normalizing second-order similarity network for few-shot learning. CoRR (2018)Google Scholar
  9. 9.
    Koniusz, P., Tas, Y., Zhang, H., Harandi, M., Porikli, F., Zhang, R.: Museum exhibit identification challenge for the supervised domain adaptation and beyond. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 815–833. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01270-0_48CrossRefGoogle Scholar
  10. 10.
    Koniusz, P., Zhang, H., Porikli, F.: A deeper look at power normalizations. In: CVPR (2018)Google Scholar
  11. 11.
    Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP, December 2008Google Scholar
  12. 12.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. TPAMI 36(3), 453–465 (2014)CrossRefGoogle Scholar
  13. 13.
    Zhang, Z., Saligrama, V.: Zero-shot learning via semantic similarity embedding. In: ICCV, pp. 4166–4174 (2015)Google Scholar
  14. 14.
    Xian, Y., Akata, Z., Sharma, G., Nguyen, Q., Hein, M., Schiele, B.: Latent embeddings for zero-shot classification. In: CVPR, pp. 69–77 (2016)Google Scholar
  15. 15.
    Frome, A., et al.: Devise: A deep visual-semantic embedding model. In: NIPS, pp. 2121–2129 (2013)Google Scholar
  16. 16.
    Changpinyo, S., Chao, W.L., Gong, B., Sha, F.: Synthesized classifiers for zero-shot learning. In: CVPR, pp. 5327–5336 (2016)Google Scholar
  17. 17.
    Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: CVPR (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.The Australian National UniversityCanberraAustralia
  2. 2.Data61/CSIROCanberraAustralia

Personalised recommendations