Abstract
Zero-shot learning (ZSL) aims to recognize unseen classes relying on the knowledge transferred from seen categories. This study presents new methods to solve two main challenges in ZSL. First, as human-annotated semantics are not discriminative enough to identify unseen classes, we propose constructing a novel latent semantic space based on the semantic attributes and designing a class-wise classifier with class-specific information maximize the discrimination of the latent semantics. Besides, to alleviate the common space’s semantic overlapping problem, we first propose constructing exclusive latent class prototypes by exclusive lasso (EL). Second, since previous ZSL methods learn visual-semantic projection between visual features and corresponding single class-level semantics directly, i.e., one-vs-all projection, which neglects the interference caused by background and noises in the image, we leverage the simple quadratic regression to soften this hard constraint. The proposed new model also alleviates the inherent domain shift problem by adopting the dual semantic auto-encoder to connect visual space, semantic space, and latent space, respectively. Comprehensive experiments on five benchmark datasets demonstrate the effectiveness of the proposed model.
Similar content being viewed by others
References
Akata Z, Perronnin F, Harchaoui Z, Schmid C (2015) Label-embedding for image classification. IEEE Trans Pattern Anal Mach Intell 38(7):1425–1438
Bartels RH, Stewart GW (1972) Solution of the Matrix Equation AX + XB = C [F4]. Commun ACM 15(9):820–826. https://doi.org/10.1145/361573.361582
Boyd S, Parikh N, Chu E (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Now Publishers Inc
Changpinyo S, Chao W.L, 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
Chen L, Zhang H, Xiao J, Liu W, Chang S.F (2018) Zero-shot visual recognition using semantics-preserving adversarial embedding networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1043–1052
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
Farhadi A, Endres I, Hoiem D, Forsyth D (2009) Describing objects by their attributes. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 1778–1785. IEEE
Frome A, Corrado G, Shlens J, Bengio S, Dean J, Ranzato M, Mikolov T (2013) Devise: A deep visual-semantic embedding model
Fu Y, Hospedales TM, Xiang T, Gong S (2015) Transductive multi-view zero-shot learning. IEEE Trans Pattern Anal Mach Intell 37(11):2332–2345
Guo Y, Din, G, Han J, Yan C, Zhang J, Dai Q (2019) Landmark selection for zero-shot learning. In: IJCAI, pp. 2435–2441
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
Jia Z, Zhang Z, Wang L, Shan C, Tan T (2020) Deep unbiased embedding transfer for zero-shot learning. IEEE Trans Image Process 29:1958–1971
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
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
Lampert C.H, 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, pp. 951–958. IEEE
Li J, Lan X, Long Y, Liu Y, Chen X, Shao L, Zheng N (2020) A joint label space for generalized zero-shot classification. IEEE Trans Image Process 29:5817–5831
Liu J, Li X, Yang G (2018) Cross-class sample synthesis for zero-shot learning. In: BMVC, p. 113
Liu L, Zhou T, Long G, Jiang J, Zhang C (2020) Attribute propagation network for graph zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4868–4875
Liu Y, Tuytelaars T (2020) A deep multi-modal explanation model for zero-shot learning. IEEE Trans Image Process 29:4788–4803
Liu Y, Xie D.Y, Gao Q, Han J, Wang S, Gao X (2019) Graph and autoencoder based feature extraction for zero-shot learning. In: IJCAI, pp. 3038–3044
Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. Journal of machine learning research 9(11)
Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. arXiv preprint arXiv:1310.4546
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
Norouzi M, Mikolov T, Bengio S, Singer Y, Shlens J, Frome A, Corrado G.S, Dean J (2013) Zero-shot learning by convex combination of semantic embeddings. arXiv preprint arXiv:1312.5650
Pambala A, Dutta T, Biswas S (2020) Generative model with semantic embedding and integrated classifier for generalized zero-shot learning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1237–1246
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
Romera-Paredes B, Torr P (2015) An embarrassingly simple approach to zero-shot learning. In: International conference on machine learning, pp. 2152–2161. PMLR (2015)
Socher R, Ganjoo M, Manning C.D, Ng A (2013) Zero-shot learning through cross-modal transfer. In NIPS
Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset
Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B (2016) Latent embeddings for zero-shot classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 69–77
Xian Y, Lampert CH, Schiele B, Akata Z (2018) Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans Pattern Anal Mach Intell 41(9):2251–2265
Xie Z, Cao W, Ming Z (2021) A further study on biologically inspired feature enhancement in zero-shot learning. Int J Mach Learn Cybernet 12(1):257–269
Zhang C, Wu T, Zhang Y, Zhao B, Wang T, Cui C, Yin Y (2021) Deep semantic-aware network for zero-shot visual urban perception. International Journal of Machine Learning and Cybernetics pp. 1–15
Zhang H, Koniusz P (2018) Zero-shot kernel learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7670–7679
Zhang H, Long Y, Guan Y, Shao L (2019) Triple verification network for generalized zero-shot learning. IEEE Trans Image Process 28(1):506–517
Zhang H, Long Y, Zhao C (2018) Attribute relaxation from class level to instance level for zero-shot learning. Electron Lett 54(20):1170–1172
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
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
Zhou Y, Jin R, Hoi S.C.H (2010) Exclusive lasso for multi-task feature selection. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp. 988–995. JMLR Workshop and Conference Proceedings
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Mi, JX., Zhang, Z., Tai, D. et al. Learning exclusive discriminative semantic information for zero-shot learning. Int. J. Mach. Learn. & Cyber. 14, 761–772 (2023). https://doi.org/10.1007/s13042-022-01661-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01661-0