Skip to main content

2019 | OriginalPaper | Buchkapitel

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

verfasst von : Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu

Erschienen in: MultiMedia Modeling

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

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.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1
AwA2 was recently proposed in [25] as a replacement for the Animals with Attributes (AwA) dataset [15] whose images are not publicly available.
 
Literatur
1.
Zurück zum Zitat Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(7), 1425–1438 (2016)CrossRef Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(7), 1425–1438 (2016)CrossRef
2.
Zurück zum Zitat 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) 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)
3.
Zurück zum Zitat Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)MATH Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)MATH
4.
Zurück zum Zitat Bucher, M., Herbin, S., Jurie, F.: Generating visual representations for zero-shot classification. In: ICCV Workshops: TASK-CV. IEEE (2017) Bucher, M., Herbin, S., Jurie, F.: Generating visual representations for zero-shot classification. In: ICCV Workshops: TASK-CV. IEEE (2017)
5.
Zurück zum Zitat 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) 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)
6.
7.
Zurück zum Zitat 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) 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)
8.
Zurück zum Zitat Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Proceedings of the NIPS 2013, pp. 2121–2129 (2013) Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Proceedings of the NIPS 2013, pp. 2121–2129 (2013)
9.
Zurück zum Zitat 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)CrossRef 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)CrossRef
10.
Zurück zum Zitat 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) 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)
11.
Zurück zum Zitat 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) 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)
12.
Zurück zum Zitat Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: Proceedings of the CVPR 2017, pp. 4447–4456. IEEE (2017) Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: Proceedings of the CVPR 2017, pp. 4447–4456. IEEE (2017)
13.
Zurück zum Zitat 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) 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)
14.
Zurück zum Zitat 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) 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)
15.
Zurück zum Zitat 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)CrossRef 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)CrossRef
16.
Zurück zum Zitat Larochelle, H., Erhan, D., Bengio, Y.: Zero-data learning of new tasks. In: AAAI, vol. 1, p. 3 (2008) Larochelle, H., Erhan, D., Bengio, Y.: Zero-data learning of new tasks. In: AAAI, vol. 1, p. 3 (2008)
17.
Zurück zum Zitat 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) 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)
18.
Zurück zum Zitat Radovanović, M., Nanopoulos, A., Ivanović, M.: Hubs in space: popular nearest neighbors in high-dimensional data. J. Mach. Learn. Res. 11, 2487–2531 (2010)MathSciNetMATH Radovanović, M., Nanopoulos, A., Ivanović, M.: Hubs in space: popular nearest neighbors in high-dimensional data. J. Mach. Learn. Res. 11, 2487–2531 (2010)MathSciNetMATH
19.
Zurück zum Zitat Rohrbach, M., Ebert, S., Schiele, B.: Transfer learning in a transductive setting. In: Proceedings of the NIPS 2013, pp. 46–54 (2013) Rohrbach, M., Ebert, S., Schiele, B.: Transfer learning in a transductive setting. In: Proceedings of the NIPS 2013, pp. 46–54 (2013)
20.
Zurück zum Zitat Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: Proceedings of the ICML 2015, pp. 2152–2161 (2015) Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: Proceedings of the ICML 2015, pp. 2152–2161 (2015)
21.
Zurück zum Zitat 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_9CrossRef 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_​9CrossRef
22.
Zurück zum Zitat Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the CVPR 2015, pp. 1–9. IEEE (2015) Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the CVPR 2015, pp. 1–9. IEEE (2015)
23.
Zurück zum Zitat Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011) Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)
25.
Zurück zum Zitat 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) 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.
Zurück zum Zitat Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the CVPR 2018. IEEE (2018) Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the CVPR 2018. IEEE (2018)
27.
Zurück zum Zitat 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) 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)
Metadaten
Titel
From Classical to Generalized Zero-Shot Learning: A Simple Adaptation Process
verfasst von
Yannick Le Cacheux
Hervé Le Borgne
Michel Crucianu
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-05716-9_38