Skip to main content
Erschienen in: Cognitive Computation 4/2019

07.03.2019

Discriminant Zero-Shot Learning with Center Loss

verfasst von: Xiao-Bo Jin, Guo-Sen Xie, Kaizhu Huang, Heling Cao, Qiu-Feng Wang

Erschienen in: Cognitive Computation | Ausgabe 4/2019

Einloggen

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

search-config
loading …

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.

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!

Literatur
1.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Akata Z, Perronnin F, Harchaoui Z, Schmid C. Label-Embedding for image classification. IEEE Trans Pattern Anal Mach Intell 2016;38(7):1425–38.CrossRefPubMed Akata Z, Perronnin F, Harchaoui Z, Schmid C. Label-Embedding for image classification. IEEE Trans Pattern Anal Mach Intell 2016;38(7):1425–38.CrossRefPubMed
3.
Zurück zum Zitat 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. 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.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res 2012;13:281–305. Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res 2012;13:281–305.
6.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Changpinyo S, Chao W-L, Gong B, Sha F. 2016. Synthesized Classifiers for Zero-Shot. Learning, p. 5327–5336. Changpinyo S, Chao W-L, Gong B, Sha F. 2016. Synthesized Classifiers for Zero-Shot. Learning, p. 5327–5336.
8.
Zurück zum Zitat Changpinyo S, Chao W-L, Sha F. 2016. Predicting visual exemplars of unseen classes for zero-Shot learning. In: ICCV 2017. Changpinyo S, Chao W-L, Sha F. 2016. Predicting visual exemplars of unseen classes for zero-Shot learning. In: ICCV 2017.
9.
Zurück zum Zitat 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. 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.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Jayaraman D, Grauman K. 2014. Zero-shot recognition with unreliable attributes. In: Advances in neural information processing systems, p. 3464–3472. Jayaraman D, Grauman K. 2014. Zero-shot recognition with unreliable attributes. In: Advances in neural information processing systems, p. 3464–3472.
12.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Jin X-B, Geng G-G, Xie G-S, Huang K. Approximately optimizing NDCG using pair-wise loss. Inf Sci 2018;453:50–65.CrossRef Jin X-B, Geng G-G, Xie G-S, Huang K. Approximately optimizing NDCG using pair-wise loss. Inf Sci 2018;453:50–65.CrossRef
14.
Zurück zum Zitat Jin X-B, Xie G-S, Huang K, Hussain A. 2018. Accelerating infinite ensemble of clustering by pivot features. Cognitive Computation, p. 1–9. 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.
Zurück zum Zitat Jin X-B, Zhang X-Y, Huang K, Geng G-G. 2017. Stochastic Conjugate Gradient Algorithm with Variance Reduction. arXiv:1710.09979. Jin X-B, Zhang X-Y, Huang K, Geng G-G. 2017. Stochastic Conjugate Gradient Algorithm with Variance Reduction. arXiv:1710.​09979.
16.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Kodirov E, Xiang T, Fu Z, Gong S. 2015. Unsupervised domain adaptation for zero-Shot learning. In: ICCV 2015, p. 2452–2460. Kodirov E, Xiang T, Fu Z, Gong S. 2015. Unsupervised domain adaptation for zero-Shot learning. In: ICCV 2015, p. 2452–2460.
18.
Zurück zum Zitat 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.CrossRefPubMed 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.CrossRefPubMed
19.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Li Y, Zhang J, Xhang J, Huang K. 2018. Discriminative learning of latent features for zero-Shot recognition. Li Y, Zhang J, Xhang J, Huang K. 2018. Discriminative learning of latent features for zero-Shot recognition.
21.
Zurück zum Zitat Loshchilov I, Hutter F. 2017. SGDR Stochastic gradient descent with warm restarts. In: ICLR 2017. Loshchilov I, Hutter F. 2017. SGDR Stochastic gradient descent with warm restarts. In: ICLR 2017.
22.
Zurück zum Zitat 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. 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.
Zurück zum Zitat 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. 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.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Romera-Paredes B, Torr PHS. 2015. An Embarrassingly Simple Approach to Zero-shot Learning. In: ICML, ICML’15, Lille, p. 2152–2161. JMLR.org. 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.
Zurück zum Zitat 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.CrossRefPubMed 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.CrossRefPubMed
27.
Zurück zum Zitat 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. 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.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Spratling MW. A hierarchical predictive coding model of object recognition in natural images. Cogn Comput 2017;9(2):151– 67.CrossRef Spratling MW. A hierarchical predictive coding model of object recognition in natural images. Cogn Comput 2017;9(2):151– 67.CrossRef
30.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B. 2016. Latent Embeddings for Zero-shot Classification. In: CVPR 2016. Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B. 2016. Latent Embeddings for Zero-shot Classification. In: CVPR 2016.
32.
Zurück zum Zitat Xian Y, Schiele B, Akata Z. 2017. Zero-Shot Learning - The Good, the Bad and the Ugly. In: CVPR 2017, arXiv:1703.04394. Xian Y, Schiele B, Akata Z. 2017. Zero-Shot Learning - The Good, the Bad and the Ugly. In: CVPR 2017, arXiv:1703.​04394.
33.
Zurück zum Zitat 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.CrossRef 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.CrossRef
34.
Zurück zum Zitat Yang FSY, Zhang L, Xiang T, Torr PHS, Hospedales TM. 2018. Learning to compare: Relation network for few-shot learning. Yang FSY, Zhang L, Xiang T, Torr PHS, Hospedales TM. 2018. Learning to compare: Relation network for few-shot learning.
35.
Zurück zum Zitat 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. 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.
Zurück zum Zitat Zhang Z, Saligrama V. 2015. Zero-Shot learning via semantic similarity embedding. In: ICCV 2015. p. 4166–4174. Zhang Z, Saligrama V. 2015. Zero-Shot learning via semantic similarity embedding. In: ICCV 2015. p. 4166–4174.
37.
Zurück zum Zitat Zhang Ziming, Saligrama V. 2016. Zero-Shot Learning via Joint Latent Similarity Embedding, p. 6034–6042. Zhang Ziming, Saligrama V. 2016. Zero-Shot Learning via Joint Latent Similarity Embedding, p. 6034–6042.
38.
Zurück zum Zitat Zhong G, Zheng Y, Zhang X-Y, Wei H, Ling X. 2018. Convolutional discriminant analysis. In: ICPR 2018, p. 6. Zhong G, Zheng Y, Zhang X-Y, Wei H, Ling X. 2018. Convolutional discriminant analysis. In: ICPR 2018, p. 6.
Metadaten
Titel
Discriminant Zero-Shot Learning with Center Loss
verfasst von
Xiao-Bo Jin
Guo-Sen Xie
Kaizhu Huang
Heling Cao
Qiu-Feng Wang
Publikationsdatum
07.03.2019
Verlag
Springer US
Erschienen in
Cognitive Computation / Ausgabe 4/2019
Print ISSN: 1866-9956
Elektronische ISSN: 1866-9964
DOI
https://doi.org/10.1007/s12559-019-09629-z

Weitere Artikel der Ausgabe 4/2019

Cognitive Computation 4/2019 Zur Ausgabe