More Web Proxy on the site http://driver.im/

research-article

Zero-Shot Learning With Transferred Samples

Authors:

Yue GaoAuthors Info & Claims

IEEE Transactions on Image Processing, Volume 26, Issue 7

Pages 3277 - 3290

https://doi.org/10.1109/TIP.2017.2696747

Published: 01 July 2017 Publication History

Abstract

By transferring knowledge from the abundant labeled samples of known source classes, zero-shot learning (ZSL) makes it possible to train recognition models for novel target classes that have no labeled samples. Conventional ZSL approaches usually adopt a two-step recognition strategy, in which the test sample is projected into an intermediary space in the first step, and then the recognition is carried out by considering the similarity between the sample and target classes in the intermediary space. Due to this redundant intermediate transformation, information loss is unavoidable, thus degrading the performance of overall system. Rather than adopting this two-step strategy, in this paper, we propose a novel one-step recognition framework that is able to perform recognition in the original feature space by using directly trained classifiers. To address the lack of labeled samples for training supervised classifiers for the target classes, we propose to transfer samples from source classes with pseudo labels assigned, in which the transferred samples are selected based on their transferability and diversity. Moreover, to account for the unreliability of pseudo labels of transferred samples, we modify the standard support vector machine formulation such that the unreliable positive samples can be recognized and suppressed in the training phase. The entire framework is fairly general with the possibility of further extensions to several common ZSL settings. Extensive experiments on four benchmark data sets demonstrate the superiority of the proposed framework, compared with the state-of-the-art approaches, in various settings.

References

[1]

C. M. Bishop, Pattern Recognition and Machine Learning, vol. Volume 1 . New York, NY, USA: Springer, 2006.

Digital Library

[2]

S. Changpinyo, W.-L. Chao, B. Gong, and F. Sha, “ Synthesized classifiers for zero-shot learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 5327–5336.

[3]

C. H. Lampert, H. Nickisch, and S. Harmeling, “ Attribute-based classification for zero-shot visual object categorization,” IEEE Trans. Pattern Anal. Mach. Intell., vol. Volume 36, no. Issue 3, pp. 453–465, 2014.

Digital Library

[4]

A. Farhadi, I. Endres, D. Hoiem, and D. A. Forsyth, “ Describing objects by their attributes,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., Jun. 2009, pp. 1778–1785.

[5]

R. Socher, M. Ganjoo, C. D. Manning, and A. Y. Ng, “ Zero-shot learning through cross-modal transfer,” in Proc. 27th Annu. Conf. Neural Inf. Process. Syst., 2013, pp. 935–943.

Digital Library

[6]

C. H. Lampert, H. Nickisch, and S. Harmeling, “ Learning to detect unseen object classes by between-class attribute transfer,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., Jun. 2009, pp. 951–958.

[7]

B. Romera-Paredes and P. Torr, “ An embarrassingly simple approach to zero-shot learning,” in Proc. 32nd Int. Conf. Mach. Learn., 2015, pp. 2152–2161.

Digital Library

[8]

Y. Fu, T. M. Hospedales, T. Xiang, Z. Fu, and S. Gong, “ Transductive multi-view embedding for zero-shot recognition and annotation,” in Proc. 13th Eur. Conf. Comput. Vis. (ECCV), 2014, pp. 584–599.

[9]

Y. Guo, G. Ding, X. Jin, and J. Wang, “ Transductive zero-shot recognition via shared model space learning,” in Proc. 30th AAAI Conf. Artif. Intell., 2016, pp. 3434–3500.

Digital Library

[10]

E. Kodirov, T. Xiang, Z. Fu, and S. Gong, “ Unsupervised domain adaptation for zero-shot learning,” in Proc. IEEE Int. Conf. Comput. Vis., Dec. 2015, pp. 2452–2460.

Digital Library

[11]

Z. Ji, Y. Xie, Y. Pang, L. Chen, and Z. Zhang. (2016). “ Zeroshot learning with multi-battery factor analysis .” {Online}. Available: https://arxiv.org/abs/1606.09349

[12]

X. Li, S. Liao, W. Lan, X. Du, and G. Yang, “ Zero-shot image tagging by hierarchical semantic embedding,” in Proc. 38th Int. ACM SIGIR Conf. Res. Develop. Inf. Retr., 2015, pp. 879–882.

Digital Library

[13]

Z. Fu, T. A. Xiang, E. Kodirov, and S. Gong, “ Zero-shot object recognition by semantic manifold distance,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 2635–2644.

[14]

M. Norouzi et al. (2013). “ Zero-shot learning by convex combination of semantic embeddings .” {Online}. Available: https://arxiv.org/abs/1312.5650

[15]

D. Bertsekas, Nonlinear Programming . Belmont, MA, USA: Athena Scientific, 1999.

[16]

G. Ding, Y. Guo, J. Zhou, and Y. Gao, “ Large-scale cross-modality search via collective matrix factorization hashing,” IEEE Trans. Image Process., vol. Volume 25, no. Issue 11, pp. 5427–5440, 2016.

Digital Library

[17]

Z. Lin, G. Ding, J. Han, and J. Wang, “ Cross-view retrieval via probability-based semantics-preserving hashing,” IEEE Trans. Cybern., to be published. pub-id-type=doi>10.1109/TCYB.2016.2608906</object-id>.

[18]

D. Zhang, J. Han, J. Han, and L. Shao, “ Cosaliency detection based on intrasaliency prior transfer and deep intersaliency mining,” IEEE Trans. Neural Netw. Learn. Syst., vol. Volume 27, no. Issue 6, pp. 1163–1176, 2016.

[19]

X. Lu, Y. Yuan, and X. Zheng, “ Joint dictionary learning for multispectral change detection,” IEEE Trans. Cybern., vol. Volume 47, no. Issue 4, pp. 884–897, 2017.

[20]

L. J. Ba, K. Swersky, S. Fidler, and R. Salakhutdinov, “ Predicting deep zero-shot convolutional neural networks using textual descriptions,” in Proc. IEEE Int. Conf. Comput. Vis. ICCV, Santiago, Chile, Dec. 2015, pp. 4247–4255.

Digital Library

[21]

Z. Zhang and V. Saligrama, “ Zero-shot learning via semantic similarity embedding,” in Proc. IEEE Int. Conf. Comput. Vis., Jun. 2015, pp. 4166–4174.

Digital Library

[22]

M. Rohrbach, S. Ebert, and B. Schiele, “ Transfer learning in a transductive setting,” in Proc. 27th Annu. Conf. Neural Inf. Process. Syst., 2013, pp. 46–54.

Digital Library

[23]

A. Krizhevsky, “ Learning multiple layers of features from tiny images,” <institution content-type=department>Dept. Comput. Sci</institution>., <institution content-type=institution>Univ. Toronto</institution>, Toronto, ON, Canada, Tech. Rep., 2009.

[24]

L. van der Maaten and G. Hinton, “ Visualizing data using t-SNE,” J. Mach. Learn. Res., vol. Volume 9, nos. Issue 2579</issue>–<issue>2605, p. pp.85, 2008.

[25]

M. Belkin and P. Niyogi, “ Laplacian eigenmaps and spectral techniques for embedding and clustering,” in Proc. Adv. Neural Inf. Process. Syst., vol. Volume 14 . 2001, pp. 585–591.

Digital Library

[26]

F. Delbos and J. C. Gilbert, “ Global linear convergence of an augmented lagrangian algorithm for solving convex quadratic optimization problems,” Ph.D. dissertation, <institution content-type=institution>INRIA</institution>, France, 2003.

[27]

D. A. Spielman and S.-H. Teng, “ Nearly-linear time algorithms for graph partitioning, graph sparsification, and solving linear systems,” in Proc. 36th Annu. ACM Symp. Theory Comput., 2004, pp. 81–90.

Digital Library

[28]

V. Vapnik, Statistical Learning Theory . Hoboken, NJ, USA: Wiley, 1998.

[29]

C.-W. Hsu and C.-J. Lin, “ A comparison of methods for multiclass support vector machines,” IEEE Trans. Neural Netw., vol. Volume 13, no. Issue 2, pp. 415–425, 2002.

Digital Library

[30]

H. Xiao, H. Xiao, and C. Eckert, “ Adversarial label flips attack on support vector machines,” in Proc. 20th Eur. Conf. Artif. Intell. (ECAI), 2012, pp. 870–875.

Digital Library

[31]

C.-C. Chang and C.-J. Lin, “ LIBSVM: A library for support vector machines,” ACM Trans. Intell. Syst. Technol., vol. Volume 2, no. Issue 3, pp. 27:1–27:27, 2011.

Digital Library

[32]

M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, The PASCAL Visual Object Classes Challenge 2008 (VOC2008) Results, accessed on 2008. {Online}. Available: http://www.pascal-network.org/challenges/VOC/voc2008/workshop/index.html

[33]

C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, “ The caltech-UCSD birds-200-2011 dataset,” <institution content-type=institution>California Inst. Technol</institution>., Pasadena, CA, USA, Tech. Rep. CNS-TR-2011-001, 2011.

[34]

Y. Guo, G. Ding, L. Liu, J. Han, and L. Shao, “ Learning to hash with optimized anchor embedding for scalable retrieval,” IEEE Trans. Image Process., vol. Volume 26, no. Issue 3, pp. 1344–1354, 2017.

Digital Library

[35]

X. Lu, X. Zheng, and X. Li, “ Latent semantic minimal hashing for image retrieval,” IEEE Trans. Image Process., vol. Volume 26, no. Issue 1, pp. 355–368, 2017.

Digital Library

[36]

D. Zhang, J. Han, C. Li, J. Wang, and X. Li, “ Detection of co-salient objects by looking deep and wide,” Int. J. Comput. Vis., vol. Volume 120, no. Issue 2, pp. 215–232, 2016.

Digital Library

[37]

Y. Gu, X. Qian, Q. Li, M. Wang, R. Hong, and Q. Tian, “ Image annotation by latent community detection and multikernel learning,” IEEE Trans. Image Process., vol. Volume 24, no. Issue 11, pp. 3450–3463, 2015.

[38]

J. Donahue et al., “ DeCAF: A deep convolutional activation feature for generic visual recognition,” in Proc. 31th Int. Conf. Mach. Learn., 2014, pp. 647–655.

Digital Library

[39]

K. Simonyan and A. Zisserman. (2014). “ Very deep convolutional networks for large-scale image recognition .” {Online}. Available: https://arxiv.org/abs/1409.1556

[40]

E. H. Huang, R. Socher, C. D. Manning, and A. Y. Ng, “ Improving word representations via global context and multiple word prototypes,” in Proc. 50th Annu. Meeting Assoc. Comput. Linguistics, 2012, pp. 873–882.

Digital Library

[41]

D. Jayaraman and K. Grauman, “ Zero-shot recognition with unreliable attributes,” in Proc. Annu. Conf. Neural Inf. Process. Syst., 2014, pp. 3464–3472.

Digital Library

[42]

Z. Akata, S. E. Reed, D. Walter, H. Lee, and B. Schiele, “ Evaluation of output embeddings for fine-grained image classification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 2927–2936.

[43]

X. Li, Y. Guo, and D. Schuurmans, “ Semi-supervised zero-shot classification with label representation learning,” in Proc. IEEE Int. Conf. Comput. Vis., Dec. 2015, pp. 4211–4219.

Digital Library

[44]

X. Li and Y. Guo, “ Max-margin zero-shot learning for multi-class classification,” in Proc. 18th Int. Conf. Artif. Intell. Statist., 2015, pp. 626–634.

[45]

Z. Al-Halah, M. Tapaswi, and R. Stiefelhagen, “ Recovering the missing link: Predicting class-attribute associations for unsupervised zero-shot learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 5975–5984.

[46]

Y. Xian, Z. Akata, G. Sharma, Q. N. Nguyen, M. Hein, and B. Schiele, “ Latent embeddings for zero-shot classification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, Jun. 2016, pp. 69–77.

[47]

Z. Zhang and V. Saligrama, “ Zero-shot learning via joint latent similarity embedding,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 6034–6042.

[48]

F. X. Yu, L. Cao, R. S. Feris, J. R. Smith, and S.-F. Chang, “ Designing category-level attributes for discriminative visual recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2013, pp. 771–778.

Digital Library

[49]

J. Deng et al., “ Large-scale object classification using label relation graphs,” in Proc. 13th Eur. Conf. Comput. Vis. (ECCV), 2014, pp. 48–64.

[50]

X. Qian et al., “ Image location inference by multisaliency enhancement,” IEEE Trans. Multimedia, vol. Volume 19, no. Issue 4, pp. 813–821, 2017.

Digital Library

Cited By

Lazaros KKoumadorakis DVrahatis AKotsiantis S(2024)A comprehensive review on zero-shot-learning techniquesIntelligent Decision Technologies10.3233/IDT-24029718:2(1001-1028)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.3233/IDT-240297
Gao SXu DTian YYu ZLiu BHan G(2024)Knowledge Graph-Driven Data Grafting Technique: A Study on Feature Selection and Relationship InferenceProceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms10.1145/3690407.3690588(1088-1093)Online publication date: 21-Jun-2024
https://dl.acm.org/doi/10.1145/3690407.3690588
Tan JWan JCai HChen XChen B(2024)A Deep Correlation Feature Extraction Network: Intelligent Description of Bearing Fault Knowledge for Zero-Sample LearningKnowledge Science, Engineering and Management10.1007/978-981-97-5492-2_1(3-15)Online publication date: 16-Aug-2024
https://dl.acm.org/doi/10.1007/978-981-97-5492-2_1
Show More Cited By

Zero-Shot Learning With Transferred Samples
1. Computing methodologies

Recommendations

Synthesizing samples for zero-shot learning
IJCAI'17: Proceedings of the 26th International Joint Conference on Artificial Intelligence

Zero-shot learning (ZSL) is to construct recognition models for unseen target classes that have no labeled samples for training. It utilizes the class attributes or semantic vectors as side information and transfers supervision information from related ...
Ordinal zero-shot learning
IJCAI'17: Proceedings of the 26th International Joint Conference on Artificial Intelligence

Zero-shot learning predicts new class even if no training data is available for that class. The solution to conventional zero-shot learning usually depends on side information such as attribute or text corpora. But these side information is not easy to ...
Zero-Shot Learning with Noisy Labels
Abstract
Zero-shot learning (ZSL) is an attractive technique that can recognize novel object classes without any visual examples, but most existing methods assume that the class labels of the training instances from seen classes are accurate and reliable. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE Transactions on Image Processing

IEEE Transactions on Image Processing Volume 26, Issue 7

July 2017

522 pages

ISSN:1057-7149

Issue’s Table of Contents

Copyright © 2017.

Publisher

IEEE Press

Publication History

Published: 01 July 2017

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

40
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Lazaros KKoumadorakis DVrahatis AKotsiantis S(2024)A comprehensive review on zero-shot-learning techniquesIntelligent Decision Technologies10.3233/IDT-24029718:2(1001-1028)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.3233/IDT-240297
Gao SXu DTian YYu ZLiu BHan G(2024)Knowledge Graph-Driven Data Grafting Technique: A Study on Feature Selection and Relationship InferenceProceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms10.1145/3690407.3690588(1088-1093)Online publication date: 21-Jun-2024
https://dl.acm.org/doi/10.1145/3690407.3690588
Tan JWan JCai HChen XChen B(2024)A Deep Correlation Feature Extraction Network: Intelligent Description of Bearing Fault Knowledge for Zero-Sample LearningKnowledge Science, Engineering and Management10.1007/978-981-97-5492-2_1(3-15)Online publication date: 16-Aug-2024
https://dl.acm.org/doi/10.1007/978-981-97-5492-2_1
Li YLiu ZChang XMcAuley JYao L(2023)Diversity-Boosted Generalization-Specialization Balancing for Zero-Shot LearningIEEE Transactions on Multimedia10.1109/TMM.2023.323621125(8372-8382)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1109/TMM.2023.3236211
Li YLiu ZYao LChang X(2023)Attribute-Modulated Generative Meta Learning for Zero-Shot LearningIEEE Transactions on Multimedia10.1109/TMM.2021.313921125(1600-1610)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1109/TMM.2021.3139211
Li YLiu ZYao LWang XMcAuley JChang X(2022)An Entropy-Guided Reinforced Partial Convolutional Network for Zero-Shot LearningIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2022.314790232:8(5175-5186)Online publication date: 1-Aug-2022
https://dl.acm.org/doi/10.1109/TCSVT.2022.3147902
Xu BZeng ZLian CDing Z(2021)Semi-Supervised Low-Rank Semantics Grouping for Zero-Shot LearningIEEE Transactions on Image Processing10.1109/TIP.2021.305067730(2207-2219)Online publication date: 1-Jan-2021
https://dl.acm.org/doi/10.1109/TIP.2021.3050677
Sun XGu JSun H(2021)Research progress of zero-shot learningApplied Intelligence10.1007/s10489-020-02075-751:6(3600-3614)Online publication date: 1-Jun-2021
https://dl.acm.org/doi/10.1007/s10489-020-02075-7
Hong MLi GZhang XHuang QWen Chen CCucchiara RHua XQi GRicci EZhang ZZimmermann R(2020)Generalized Zero-Shot Video Classification via Generative Adversarial NetworksProceedings of the 28th ACM International Conference on Multimedia10.1145/3394171.3413517(2419-2426)Online publication date: 12-Oct-2020
https://dl.acm.org/doi/10.1145/3394171.3413517
Wang QLiu XLiu WLiu ALiu WMei T(2020)MetaSearch: Incremental Product Search via Deep Meta-LearningIEEE Transactions on Image Processing10.1109/TIP.2020.300424929(7549-7564)Online publication date: 1-Jan-2020
https://dl.acm.org/doi/10.1109/TIP.2020.3004249
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents