{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:57:19Z","timestamp":1763665039445,"version":"build-2065373602"},"reference-count":38,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Centre for Priority Research Area Artificial Intelligence and Robotics of the Warsaw University of Technology within the Excellence Initiative","award":["IC-PL\/01\/2022\u20132023"],"award-info":[{"award-number":["IC-PL\/01\/2022\u20132023"]}]},{"name":"framework of a bilateral project between the Polish Academy of Sciences and the Romania Academy","award":["IC-PL\/01\/2022\u20132023"],"award-info":[{"award-number":["IC-PL\/01\/2022\u20132023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>There are many areas where conventional supervised machine learning does not work well, for instance, in cases with a large, or systematically increasing, number of countably infinite classes. Zero-shot learning has been proposed to address this. In generalized settings, the zero-shot learning problem represents real-world applications where test instances are present during inference. Separately, recently, there has been increasing interest in meta-classifiers, which combine the results from individual classifications to improve the overall classification quality. In this context, the purpose of the present paper is two-fold: First, the performance of five state-of-the-art, generalized zero-shot learning methods is compared for five popular benchmark datasets. Second, six standard meta-classification approaches are tested by experiment. In the experiments undertaken, all meta-classifiers were applied to the same datasets; their performance was compared to each other and to the original classifiers.<\/jats:p>","DOI":"10.3390\/info13120561","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T05:45:22Z","timestamp":1669787122000},"page":"561","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Generalized Zero-Shot Learning for Image Classification\u2014Comparing Performance of Popular Approaches"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5627-6351","authenticated-orcid":false,"given":"Elie","family":"Saad","sequence":"first","affiliation":[{"name":"Department of Mathematics and Information Science, Warsaw University of Technology, 46580 Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8069-2152","authenticated-orcid":false,"given":"Marcin","family":"Paprzycki","sequence":"additional","affiliation":[{"name":"Systems Research Institute, Polish Academy of Sciences, 46580 Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7714-4844","authenticated-orcid":false,"given":"Maria","family":"Ganzha","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Information Science, Warsaw University of Technology, 46580 Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0137-9676","authenticated-orcid":false,"given":"Amelia","family":"B\u0103dic\u0103","sequence":"additional","affiliation":[{"name":"Department of Statistics and Business Informatics, University of Craiova, 200585 Craiova, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8480-9867","authenticated-orcid":false,"given":"Costin","family":"B\u0103dic\u0103","sequence":"additional","affiliation":[{"name":"Department of Computers and Information Technology, University of Craiova, 200585 Craiova, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8484-5849","authenticated-orcid":false,"given":"Stefka","family":"Fidanova","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, 1421 Sofia, Bulgaria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5870-2588","authenticated-orcid":false,"given":"Ivan","family":"Lirkov","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, 1421 Sofia, Bulgaria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1946-0384","authenticated-orcid":false,"given":"Mirjana","family":"Ivanovi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, University of Novi Sad, 21000 Novi Sad, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chao, W.L., Changpinyo, S., Gong, B., and Sha, F. (2016, January 11\u201314). An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"ref_2","unstructured":"Joachims, T. (2003, January 21\u201324). Transductive learning via spectral graph partitioning. Proceedings of the 20th International Conference on Machine Learning (ICML-03), Washington, DC, USA."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Arnold, A., Nallapati, R., and Cohen, W.W. (2007, January 28\u201331). A comparative study of methods for transductive transfer learning. Proceedings of the Seventh IEEE international conference on data mining workshops (ICDMW 2007), Omaha, NE, USA.","DOI":"10.1109\/ICDMW.2007.109"},{"key":"ref_4","unstructured":"Palatucci, M.M. (2011). Thought Recognition: Predicting and Decoding Brain Activity Using the Zero-Shot Learning Model, Carnegie Mellon University."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1109\/TPAMI.2013.140","article-title":"Attribute-based classification for zero-shot learning of object categories","volume":"36","author":"Lampert","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","unstructured":"Larochelle, H., Erhan, D., and Bengio, Y. (2008, January 13\u201317). Zero-data learning of new tasks. Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, AAAI 2008, Chicago, IL, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Stark, M., and Schiele, B. (2011, January 20\u201325). Evaluating knowledge transfer and zero-shot learning in a large-scale setting. Proceedings of the CVPR 2011, Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yu, X., and Aloimonos, Y. (2010, January 5\u201311). Attribute-based transfer learning for object categorization with zero\/one training example. Proceedings of the European Conference on Computer Vision, Crete, Greece.","DOI":"10.1007\/978-3-642-15555-0_10"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xu, X., Shen, F., Yang, Y., Zhang, D., Tao Shen, H., and Song, J. (2017, January 21\u201326). Matrix tri-factorization with manifold regularizations for zero-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.217"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ding, Z., Shao, M., and Fu, Y. (2017, January 21\u201326). Low-rank embedded ensemble semantic dictionary for zero-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.636"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","article-title":"Zero-shot learning\u2014A comprehensive evaluation of the good, the bad and the ugly","volume":"41","author":"Xian","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., and Sloot, P.M.A. (2022, January 21\u201323). Practical Aspects of Zero-Shot Learning. Proceedings of the Computational Science\u2014ICCS 2022, London, UK.","DOI":"10.1007\/978-3-031-08757-8"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Saad, E., Paprzycki, M., and Ganzha, M. (2022). Practical Aspects of Zero-Shot Learning. arXiv.","DOI":"10.1007\/978-3-031-08754-7_12"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1007\/s10822-018-0116-z","article-title":"Comparing the performance of meta-classifiers\u2014a case study on selected imbalanced data sets relevant for prediction of liver toxicity","volume":"32","author":"Jain","year":"2018","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"ref_15","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume":"26","author":"Frome","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","article-title":"Label-embedding for image classification","volume":"38","author":"Akata","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., and Schiele, B. (2015, January 7\u201312). Evaluation of output embeddings for fine-grained image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Shalev-Shwartz, S., and Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press.","DOI":"10.1017\/CBO9781107298019"},{"key":"ref_19","unstructured":"Romera-Paredes, B., and Torr, P. (2015, January 7\u20139). An embarrassingly simple approach to zero-shot learning. Proceedings of the International Conference on Machine Learning, PMLR, Lille, France."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Xian, Y., Akata, Z., Sharma, G., Nguyen, Q., Hein, M., and Schiele, B. (2016, January 27\u201330). Latent embeddings for zero-shot classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref_21","unstructured":"Socher, R., Ganjoo, M., Sridhar, H., Bastani, O., Manning, C.D., and Ng, A.Y. (2013). Zero-shot learning through cross-modal transfer. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., and Saligrama, V. (2015, January 7\u201313). Zero-shot learning via semantic similarity embedding. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.474"},{"key":"ref_23","unstructured":"Norouzi, M., Mikolov, T., Bengio, S., Singer, Y., Shlens, J., Frome, A., Corrado, G.S., and Dean, J. (2013). Zero-shot learning by convex combination of semantic embeddings. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Chao, W.L., Gong, B., and Sha, F. (2016, January 27\u201330). Synthesized classifiers for zero-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.575"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Verma, V.K., and Rai, P. (2017, January 18\u201322). A simple exponential family framework for zero-shot learning. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Skopje, Macedonia.","DOI":"10.1007\/978-3-319-71246-8_48"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ye, M., and Guo, Y. (2017, January 21\u201326). Zero-shot classification with discriminative semantic representation learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.542"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1023\/A:1021709817809","article-title":"Combining classifiers with meta decision trees","volume":"50","author":"Todorovski","year":"2003","journal-title":"Mach. Learn."},{"key":"ref_28","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_29","unstructured":"Abreu, M.d.C., and Canuto, A.M. (2006, January 16\u201321). Analyzing the benefits of using a fuzzy-neuro model in the accuracy of the neurage system: An agent-based system for classification tasks. Proceedings of the 2006 IEEE International Joint Conference on Neural Network, Vancouver, BC, Canada."},{"key":"ref_30","first-page":"76","article-title":"Consensus-based combining method for classifier ensembles","volume":"15","author":"Alzubi","year":"2018","journal-title":"Int. Arab J. Inf. Technol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.inffus.2004.04.008","article-title":"Classifier selection for majority voting","volume":"6","author":"Ruta","year":"2005","journal-title":"Inf. Fusion"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sokolova, M., Japkowicz, N., and Szpakowicz, S. (2006, January 4\u20138). Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation. Proceedings of the Australasian Joint Conference on Artificial Intelligence, Hobart, Australia.","DOI":"10.1007\/11941439_114"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1080\/01621459.1931.10503148","article-title":"The nature and use of the harmonic mean","volume":"26","author":"Ferger","year":"1931","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_34","unstructured":"Nwankpa, C., Ijomah, W., Gachagan, A., and Marshall, S. (2018). Activation functions: Comparison of trends in practice and research for deep learning. arXiv."},{"key":"ref_35","unstructured":"Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., and Perona, P. (2010). Caltech-UCSD Birds 200, California Institute of Technology. Technical Report 2010-001."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Patterson, G., and Hays, J. (2012, January 16\u201321). Sun attribute database: Discovering, annotating, and recognizing scene attributes. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., and Forsyth, D. (2009, January 20\u201325). Describing objects by their attributes. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Demertzis, K., and Iliadis, L. (2020). GeoAI: A model-agnostic meta-ensemble zero-shot learning method for hyperspectral image analysis and classification. Algorithms, 13.","DOI":"10.3390\/a13030061"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/12\/561\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:30:18Z","timestamp":1760146218000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/12\/561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":38,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["info13120561"],"URL":"https:\/\/doi.org\/10.3390\/info13120561","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2022,11,30]]}}}