Abstract
Zero-shot learning is an essential paradigm for learning novel concepts, i.e., those whose instances were unavailable during training. Dictionary learning approaches have shown recent success in zero-shot applications. However, learning a single dictionary for a complete dataset is time-consuming and prone to underfitting. In this work, we propose Meta − DZSL, a novel meta-dictionary learning-based framework for learning dictionaries in an episodic manner. The source dataset is divided among different episodes in the proposed framework, and target domain data are common for each episode. The parameters learned in one episode become the initializations for the parameters to be learned in the next episode so that at the end of the last episode, optimal parameters are obtained. In our experiments, the data in the two domains come from the same modality. In addition, the base learner in the conventional setting is updated to perform recognition in the generalized setting. We experimented with and without noise on AWA2, SUN, CUB, and all superclasses of the LAD dataset. The results show that the proposed Meta − DZSL is robust to noise, fast, and achieves state-of-the-art results for the LAD − Fruits dataset. For all other datasets, the performance of the proposed approach remains robust and comparable to state-of-the-art results, and the training is computationally less expensive.
Similar content being viewed by others
References
Sen PC, Hajra M, Ghosh M (2020) Supervised classification algorithms in machine learning: A survey and review. In: Emerging Technology in Modelling and Graphics. Springer, pp 99–111
Alom MZ, Taha TM, Yakopcic C, Westberg S, Sidike P, Nasrin MS, Hasan M, VanEssen BC, Awwal AbdulAS, Asari VK (2019) A state-of-the-art survey on deep learning theory and architectures. Electronics 8(3):292
Wu X, Sahoo D, Hoi SCH (2020) Recent advances in deep learning for object detection. Neurocomputing
Latif S, Rana R, Khalifa S, Jurdak R, Qadir J, Schuller BW (2020) Deep representation learning in speech processing: Challenges, recent advances, and future trends. arXiv:2001.00378
Newman MEJ (2005) Power laws, pareto distributions and zipf’s law. Contemp Phys 46(5):323–351. https://doi.org/10.1080/00107510500052444
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22 (10):1345–1359
Ruder S, Peters ME, Swayamdipta S, Wolf T (2019) Transfer learning in natural language processing. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials, pp 15–18
Zhang J, Li W, Ogunbona P, Xu D (2019) Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective. ACM Comput Surv (CSUR) 52(1):1–38
Tan C, Sun F, Kong T, Zhang W, Yang C, Liu C (2018) A survey on deep transfer learning. In: International conference on artificial neural networks. Springer, pp 270–279
Ribani R, Marengoni M (2019) A survey of transfer learning for convolutional neural networks. In: 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T). IEEE, pp 47–57
Soni AN (2018) Application and analysis of transfer learning-survey. Int J Sci Res Eng Dev 1 (2):272–278
Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: A survey on few-shot learning. ACM Comput Surv (CSUR) 53(3):1–34
Kadam S, Vaidya V (2018) Review and analysis of zero, one and few shot learning approaches. In: International Conference on Intelligent Systems Design and Applications. Springer , pp 100–112
Elsken T, Staffler B, Metzen JH, Hutter F (2020) Meta-learning of neural architectures for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 12365–12375
Wang W, Zheng VW, Yu H, Miao C (2019) A survey of zero-shot learning: Settings, methods, and applications. ACM Trans Intell Syst Technol (TIST) 10(2):1–37
Fu Y, Xiang T, Jiang Y-G, Xue X, Sigal L, Gong S (2018) Recent advances in zero-shot recognition: Toward data-efficient understanding of visual content. IEEE Signal Proc Mag 35(1):112–125
Cao W, Zhou C, Wu Y, Ming Z, Xu Z, Zhang J (2020) Research progress of zero-shot learning beyond computer vision. In: International Conference on Algorithms and Architectures for Parallel Processing. Springer, pp 538–551
Sun X, Gu J, Sun H (2021) Research progress of zero-shot learning. Appl Intell 51 (6):3600–3614
Yang C, Wu W, Wang Y, Zhou H (2021) A novel feature-based model for zero-shot object detection with simulated attributes. Appl Intell:1–10
Zhang L, Xiang T, Gong S (2017) Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2021–2030
Xu X, Shen F, Yang Y, Zhang D, TaoShen H, Song J (2017) Matrix tri-factorization with manifold regularizations for zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3798–3807
Xu X, Hospedales T, Gong S (2017) Transductive zero-shot action recognition by word-vector embedding. Int J Comput Vis 123(3):309–333
Ye M, Guo Y (2017) Zero-shot classification with discriminative semantic representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7140–7148
Ji Z, Cui B, Yu Y, Pang Y, Zhang Z (2021) Zero-shot classification with unseen prototype learning. Neural Comput Appl:1–11
Li X, Zhang D, Ye M, Li X, Dou Q, Lv Q (2020) Bidirectional generative transductive zero-shot learning. Neural Comput Appl:1–14
Fu Y, Hospedales TM, Xiang T, Fu Z, Gong S (2014) Transductive multi-view embedding for zero-shot recognition and annotation. In: European Conference on Computer Vision. Springer, pp 584–599
Kodirov E, Xiang T, Fu Z, Gong S (2015) Unsupervised domain adaptation for zero-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2452–2460
Singh UP, Singh KP, Thakur M (2021) Nucnormzsl: nuclear norm-based domain adaptation in zero-shot learning. Neural Comput Appl. https://doi.org/10.1007/s00521-021-06461-1
Vanschoren J (2019) Meta-learning:35–61
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
Xiao J, Hays J, Ehinger KA, Oliva A, Torralba A (2010) Sun database: Large-scale scene recognition from abbey to zoo. In: 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 3485–3492
Zhao B, Fu Y, Liang R, Wu J, Wang Y, Wang Y (2019) A large-scale attribute dataset for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp 0–0
Akata Z, Perronnin F, Harchaoui Z, Schmid C (2015) Label-embedding for image classification. IEEE Trans Pattern Anal Mach Intell 38(7):1425–1438
Li Y, Wang D, Hu H, Lin Y, Zhuang Y (2017) Zero-shot recognition using dual visual-semantic mapping paths, pp 3279–3287
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
Jayaraman D, Grauman K (2014) Zero-shot recognition with unreliable attributes. In: Advances in neural information processing systems, pp 3464–3472
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
Jiang H, Wang R, Shan S, Chen X (2019) Transferable contrastive network for generalized zero-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp 9765–9774
Hayashi T, Fujita H, Hernandez-Matamoros A (2021) Less complexity one-class classification approach using construction error of convolutional image transformation network. Inf Sci 560:217–234
Recht B, Fazel M, Parrilo PA (2010) Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev 52(3):471–501
Fazel M, Hindi H, Boyd SP (2001) A rank minimization heuristic with application to minimum order system approximation. In: Proceedings of the 2001 American Control Conference.(Cat. No. 01CH37148), vol 6. IEEE, pp 4734–4739
Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: An unsupervised approach. In: 2011 international conference on computer vision. IEEE, pp 999–1006
KumarVerma V, Arora G, Mishra A, Rai P (2018) Generalized zero-shot learning via synthesized examples. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4281–4289
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
Chao W-L, Changpinyo S, Gong B, Sha F 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
Huang H, Wang C, Yu PS, Wang C-D Generative dual adversarial network for generalized zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 801810
Zhu P, Wang H, Saligrama V Generative dual adversarial network for generalized zero-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 801810
Huynh D, Elhamifar E Fine-grained generalized zeroshot learning via dense attribute-based attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 44834493
Verma VK, Brahma D, Rai P Meta-learning for generalized zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 6062-6069
Demertzis K, Iliadis L Geoai: A model-agnostic metaensemble zero-shot learning method for hyperspectral image analysis and classification. Algorithms 13(3):61
Verma VK, Mishra A, Pandey A, Murthy HA, Rai P Towards zero-shot learning with fewer seen class examples. In: Proceedings of the IEEE/CVFWinter Conference on Applications of Computer Vision, pp 22412251
Hu RL, Xiong C, Socher R (2018) Correction networks: Meta-learning for zero-shot learning
Soh JW, Cho S, Cho NI (2020) Meta-transfer learning for zero-shot super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 3516–3525
Abbasifard MR, Ghahremani B, Naderi H (2014) A survey on nearest neighbor search methods. Int J Comput Appl 95(25)
Zhu X, Ghahramani Z (2002) Learning from labeled and unlabeled data with label propagation
Miranda B (2020) An empirical study of meta-learning: a step towards rigorously understanding meta-learning algorithms
Hospedales T, Antoniou A, Micaelli P, Storkey A (2020) Meta-learning in neural networks: A survey. arXiv:2004.05439
Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, Xiong H, He Q (2020) A comprehensive survey on transfer learning. Proc IEEE 109(1):43–76
Agrawal R, Singh UP, Singh KP Few shots learning: Caricature to image recognition using improved relation network. In: International Conference on Computer Vision and Image Processing. Springer, pp 162173
Xian Y, Schiele B, Akata Z (2017) Zero-shot learning-the good, the bad and the ugly. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4582–4591
Li K, Min MR, Fu Y Rethinking zero-shot learning: A conditional visual classification perspective. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 35833592
Li J, Jing M, Lu K, Ding Z, Zhu L, Huang Z (2019) Leveraging the invariant side of generative zero-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 7402–7411
Akata Z, Reed S, Walter D, Lee H, Schiele B (2015) Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2927–2936
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
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
Jiang H, Wang R, Shan S, Chen X (2018) Learning class prototypes via structure alignment for zero-shot recognition. In: Proceedings of the European conference on computer vision (ECCV), pp 118–134
Shen Y, Qin J, Huang L, Liu L, Zhu F, Shao L (2020) Invertible zero-shot recognition flows. In: European Conference on Computer Vision. Springer, pp 614–631
Changpinyo S, Chao W-L, Sha F (2017) Predicting visual exemplars of unseen classes for zero-shot learning. In: Proceedings of the IEEE international conference on computer vision, pp 3476–3485
Schonfeld E, Ebrahimi S, Sinha S, Darrell T, Akata Z (2019) Generalized zero-and few-shot learning via aligned variational autoencoders. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 8247–8255
Akata Z, Perronnin F, Harchaoui Z, Schmid C (2013) Label-embedding for attribute-based classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 819–826
Xie G-S, Liu L, Jin X, Zhu F, Zhang Z, Qin J, Yao Y, Shao L (2019) Attentive region embedding network for zero-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9384–9393
Sung F, Yang Y, Zhang L, Xiang T, Torr PhilipHS, Hospedales TM (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1199–1208
Wang D, Li Y, Lin Y, Zhuang Y (2016) Relational knowledge transfer for zero-shot learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp 2145– 2151
Wang Q, Chen K (2017) Zero-shot visual recognition via bidirectional latent embedding. Int J Comput Vis 124(3):356–383
Frome A, Corrado GS, Shlens J, Bengio S, Dean J, Ranzato M, Mikolov T (2013) Devise: A deep visual-semantic embedding model. In: Advances in neural information processing systems, pp 2121–2129
Palatucci M, Pomerleau D, Hinton GE, Mitchell TM (2009) Zero-shot learning with semantic output codes. Adv Neural Inf Process Syst 22:1410–1418
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
Lampert CH, Nickisch H, Harmeling S (2013) Attribute-based classification for zero-shot visual object categorization. IEEE Trans Pattern Anal Mach Intell 36(3):453–465
Zhang F, Shi G (2019) Co-representation network for generalized zero-shot learning. In: International Conference on Machine Learning. PMLR, pp 7434–7443
Sariyildiz MB, Cinbis RG (2019) Gradient matching generative networks for zero-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2168–2178
Romera-Paredes B, Torr P (2015) An embarrassingly simple approach to zero-shot learning. In: International Conference on Machine Learning, pp 2152–2161
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
Mensink T, Gavves E, Snoek CGM (2014) Costa: Co-occurrence statistics for zero-shot classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2441–2448
Zhu Y, Xie J, Liu B, Elgammal A (2019) Learning feature-to-feature translator by alternating back-propagation for generative zero-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9844–9854
Acknowledgments
We acknowledge the anonymous reviewers for providing valuable suggestions for improving our manuscript. Furthermore, we would like to acknowledge the Ministry of Education, Government of India, for financial support in carrying out our research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
All authors declare that there are no conflicts of interest in the subject matter discussed in this manuscript.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, U.P., Singh, K.P. & Thakur, M. Meta-DZSL: a meta-dictionary learning based approach to zero-shot recognition. Appl Intell 52, 15938–15960 (2022). https://doi.org/10.1007/s10489-022-03257-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03257-1