Skip to main content
SpringerLink
Log in

Attribute self-representation steered by exclusive lasso for zero-shot learning

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Zero-shot learning (ZSL) aims to recognize new unseen classes by transferring knowledge from seen classes, which assumes that both seen and unseen classes share a common semantic space. Mainstream ZSL methods focus on learning visual-semantic projection by one-vs-all strategy in which the class-level attribute vector is matched with many visual features. However, human-annotated attributes have some limitations: 1) The attribute semantics are subjective to be manually annotated, which could lead to inaccuracy. 2) Since human-annotated attributes may focus on details, some attributes are weakly associated with the object and contribute little information to recognition. Meanwhile, most ZSL methods also suffer from the severe problem of domain shift problem. Thus, in this paper, we propose a novel ZSL model to address the above problems. Specifically, we introduce the attribute relabeling approach to rectify the original attributes by exploiting the intrinsic attribute correlation information. Then, we employ the property of group-wise competition of exclusive lasso to encourage different categories to compete for prominent category-specific attributes, respectively, which benefits learning visual-semantic projection. Besides, our model integrates the encoder-decoder paradigm to alleviate the projection shift problem. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed model. In particular, in the setting of generalized ZSL, our proposed model has higher unseen class accuracy and thus achieves the highest harmonic mean value.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Boyd S, Parikh N, Chu E (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Now Publishers Inc

  2. Changpinyo S, Chao WL, Gong B, Sha F (2016) Synthesized classifiers for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5327–5336

  3. Chao WL, Changpinyo S, Gong B, Sha F (2016) An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: European conference on computer vision. Springer, pp 52–68

  4. Ding Z, Liu H (2019) Marginalized latent semantic encoder for zero-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 6191–6199

  5. Frome A, Corrado G, Shlens J, Bengio S, Dean J, Ranzato M, Mikolov T (2013) Devise: A deep visual-semantic embedding model

  6. Fu Y, Hospedales TM, Xiang T, Gong S (2015) Transductive multi-view zero-shot learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 37(11):2332–2345

    Article  Google Scholar 

  7. Guo Y, Ding G, Han J, Tang S (2018) Zero-shot learning with attribute selection. In: Thirty-second AAAI conference on artificial intelligence

  8. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  9. Jiang H, Wang R, Shan S, Yang Y, Chen X (2017) Learning discriminative latent attributes for zero-shot classification. In: Proceedings of the IEEE international conference on computer vision, pp 4223–4232

  10. Jiang H, Wang R, Shan S, Yang Y, Chen X (2017) Learning discriminative latent attributes for zero-shot classification. In: Proceedings of the IEEE international conference on computer vision, pp 4223–4232

  11. Keshari R, Singh R, Vatsa M (2020) Generalized zero-shot learning via over-complete distribution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13300–13308

  12. Kodirov E, Xiang T, Gong S (2017) Semantic autoencoder for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3174–3183

  13. Lampert CH, Nickisch H, Harmeling S (2009) Learning to detect unseen object classes by between-class attribute transfer. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, pp 951–958

  14. Li D, Liu H, Zhang Z, Lin K, Fang S, Li Z, Xiong NN (2021) Carm: Confidence-aware recommender model via review representation learning and historical rating behavior in the online platforms. Neurocomputing 455:283–296

    Article  Google Scholar 

  15. Li J, Jing M, Lu K, Zhu L, Yang Y, Huang Z (2019) From zero-shot learning to cold-start recommendation. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 4189–4196

  16. Li X, Fang M, Feng D, Li H, Wu J (2019) Prototype adjustment for zero shot classification. Signal Processing: Image Communication 74:242–252

    Google Scholar 

  17. Li Z, Liu H, Zhang Z, Liu T, Xiong NN (2021) Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Transactions on Neural Networks and Learning Systems

  18. Lin G, Fan C, Chen W, Chen Y, Zhao F (2018) Class label autoencoder for zero-shot learning. arXiv:1801.08301

  19. Liu G, Guan J, Zhang M, Zhang J, Wang Z, Lu Z (2019) Joint projection and subspace learning for zero-shot recognition. In: 2019 IEEE International conference on multimedia and expo (ICME). IEEE, pp 1228–1233

  20. Liu H, Fang S, Zhang Z, Li D, Lin K, Wang J (2021) Mfdnet: Collaborative poses perception and matrix fisher distribution for head pose estimation. IEEE Transactions on Multimedia

  21. Liu T, Liu H, Li Y, Zhang Z, Liu S (2018) Efficient blind signal reconstruction with wavelet transforms regularization for educational robot infrared vision sensing. IEEE/ASME Transactions on Mechatronics 24(1):384–394

    Article  Google Scholar 

  22. Liu T, Liu H, Li YF, Chen Z, Zhang Z, Liu S (2019) Flexible ftir spectral imaging enhancement for industrial robot infrared vision sensing. IEEE Transactions on Industrial Informatics 16(1):544–554

    Article  Google Scholar 

  23. Liu Y, Gao Q, Li J, Han J, Shao L (2018) Zero shot learning via low-rank embedded semantic autoencoder. In: IJCAI, pp 2490–2496

  24. Ming D, Ding C (2019) Robust flexible feature selection via exclusive l21 regularization. In: Proceedings of the 28th international joint conference on artificial intelligence, pp 3158–3164

  25. Norouzi M, Mikolov T, Bengio S, Singer Y, Shlens J, Frome A, Corrado GS, Dean J (2013) Zero-shot learning by convex combination of semantic embeddings. arXiv:1312.5650

  26. Patterson G, Xu C, Su H, Hays J (2014) The sun attribute database: beyond categories for deeper scene understanding. Int J Comput Vis 108(1-2):59–81

    Article  Google Scholar 

  27. Rahman S, Khan S, Porikli F (2018) A unified approach for conventional zero-shot, generalized zero-shot, and few-shot learning. IEEE Trans Image Process 27(11):5652–5667

    Article  MathSciNet  Google Scholar 

  28. Romera-Paredes B, Torr P (2015) An embarrassingly simple approach to zero-shot learning. In: International conference on machine learning. PMLR, pp 2152–2161

  29. Shen X, Yi B, Liu H, Zhang W, Zhang Z, Liu S, Xiong N (2019) Deep variational matrix factorization with knowledge embedding for recommendation system. IEEE Transactions on Knowledge and Data Engineering

  30. Shigeto Y, Suzuki I, Hara K, Shimbo M, Matsumoto Y (2015) Ridge regression, hubness, and zero-shot learning. In: Joint european conference on machine learning and knowledge discovery in databases. Springer, pp 135–151

  31. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

  32. Socher R, Ganjoo M, Sridhar H, Bastani O, Manning CD, Ng AY (2013) Zero-shot learning through cross-modal transfer. arXiv:1301.3666

  33. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  34. Wang W, Pu Y, Verma VK, Fan K, Zhang Y, Chen C, Rai P, Carin L (2018) Zero-shot learning via class-conditioned deep generative models. In: Thirty-second AAAI conference on artificial intelligence

  35. Xian Y, Lampert CH, Schiele B, Akata Z (2018) Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE Transactions on Pattern Analysis and Machine Intelligence 41 (9):2251–2265

    Article  Google Scholar 

  36. Yu Y, Ji Z, Guo J, Zhang Z (2018) Zero-shot learning via latent space encoding. IEEE Transactions on Cybernetics 49(10):3755–3766

    Article  Google Scholar 

  37. Yu Y, Ji Z, Guo J, Zhang Z (2018) Zero-shot learning via latent space encoding. IEEE Transactions on Cybernetics 49(10):3755–3766

    Article  Google Scholar 

  38. Zhang Z, Saligrama V (2016) Zero-shot learning via joint latent similarity embedding. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 6034–6042

  39. Zhang Z, Saligrama V (2016) Zero-shot learning via joint latent similarity embedding. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 6034–6042

  40. Zhang Z, Xie Y, Yang L (2018) Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6199–6208

  41. Zhu Y, Elhoseiny M, Liu B, Peng X, Elgammal A (2018) A generative adversarial approach for zero-shot learning from noisy texts. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1004–1013

Download references

Author information

Authors and Affiliations

  1. Chongqing Key Laboratory of Image cognition, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

    Jian-Xun Mi, Zhonghao Zhang & Debao Tai

  2. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

    Jian-Xun Mi, Zhonghao Zhang, Debao Tai & Li-Fang Zhou

  3. College of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

    Li-Fang Zhou

Authors
  1. Jian-Xun Mi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhonghao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Debao Tai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Li-Fang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jian-Xun Mi.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mi, JX., Zhang, Z., Tai, D. et al. Attribute self-representation steered by exclusive lasso for zero-shot learning. Appl Intell 53, 3095–3108 (2023). https://doi.org/10.1007/s10489-022-03497-1

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03497-1

Keywords

Search

Navigation