{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:37:36Z","timestamp":1779287856076,"version":"3.51.4"},"reference-count":45,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T00:00:00Z","timestamp":1620345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502143"],"award-info":[{"award-number":["61502143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Distinguished Youth Foundation of North China University of Science and Technology","award":["JQ201715"],"award-info":[{"award-number":["JQ201715"]}]},{"name":"Graduate Model class Project of Hebei Province","award":["KCJSX2019097"],"award-info":[{"award-number":["KCJSX2019097"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The supervised model based on deep learning has made great achievements in the field of image classification after training with a large number of labeled samples. However, there are many categories without or only with a few labeled training samples in practice, and some categories even have no training samples at all. The proposed zero-shot learning greatly reduces the dependence on labeled training samples for image classification models. Nevertheless, there are limitations in learning the similarity of visual features and semantic features with a predefined fixed metric (e.g., as Euclidean distance), as well as the problem of semantic gap in the mapping process. To address these problems, a new zero-shot image classification method based on an end-to-end learnable deep metric is proposed in this paper. First, the common space embedding is adopted to map the visual features and semantic features into a common space. Second, an end-to-end learnable deep metric, that is, the relation network is utilized to learn the similarity of visual features and semantic features. Finally, the invisible images are classified, according to the similarity score. Extensive experiments are carried out on four datasets and the results indicate the effectiveness of the proposed method.<\/jats:p>","DOI":"10.3390\/s21093241","type":"journal-article","created":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T22:36:24Z","timestamp":1620426984000},"page":"3241","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Zero-Shot Image Classification Based on a Learnable Deep Metric"],"prefix":"10.3390","volume":"21","author":[{"given":"Jingyi","family":"Liu","sequence":"first","affiliation":[{"name":"College of Information Engineering, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caijuan","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Information Engineering, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongjing","family":"Tu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ze","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Information Engineering, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yazhi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,7]]},"reference":[{"key":"ref_1","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017, January 22\u201325). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., and Zafeiriou, S. (2019, January 16\u201320). Arcface: Additive angular margin loss for deep face recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L., Fei, L., Yuille, A., Huang, J., and Murphy, K. (2018, January 8\u201314). Progressive neural architecture search. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref_5","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., and Mikolov, T. (2013, January 7). Devise: A deep visual-semantic embedding model. Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS), Harrahs and Harveys, Lake Tahoe, NV, USA."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, Z., and Saligrama, V. (2015, January 14\u201317). Zero-shot learning via semantic similarity embedding. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.474"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Romera-Paredes, B. (2015, January 6\u201311). An embarrassingly simple approach to zero-shot learning. Proceedings of the 32nd International Conference on Machine Learning (ICML), Lille, France.","DOI":"10.1007\/978-3-319-50077-5_2"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., and Gong, S. (2017, January 22\u201325). Semantic autoencoder for zero-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.473"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., and Gong, S. (2017, January 22\u201325). Learning a deep embedding model for zero-shot learning. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref_10","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 (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6549","DOI":"10.1109\/TIP.2020.2991527","article-title":"Deep ranking for image zero-shot multi-label classification","volume":"29","author":"Ji","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1109\/TNNLS.2019.2904991","article-title":"Attribute-guided network for cross-modal zero-shot hashing","volume":"31","author":"Ji","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., and Hospedales, T.M. (2018, January 18\u201322). Learning to Compare: Relation Network for Few-Shot Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref_14","unstructured":"Sandouk, U., and Chen, K. (2016). Multi-Label Zero-Shot Learning via Concept Embedding. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., and Harmeling, S. (2009, January 20\u201325). Learning to detect unseen object classes by between-class attribute transfer. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-020-3032-8","article-title":"Triple discriminator generative adversarial network for zero-shot image classification","volume":"64","author":"Ji","year":"2021","journal-title":"Sci. China Inf. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105847","DOI":"10.1016\/j.knosys.2020.105847","article-title":"Multi-modal generative adversarial network for zero-shot learning","volume":"197","author":"Ji","year":"2020","journal-title":"Knowl. Based Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"167584","DOI":"10.1109\/ACCESS.2019.2953454","article-title":"Cross-layer autoencoder for zero-shot learning","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_19","unstructured":"Yu, H., and Lee, B. (2019). Zero-shot learning via simultaneous generating and learning. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shen, Y., Qin, J., Huang, L., Liu, L., Zhu, F., and Shao, L. (2020, January 23\u201328). Invertible zero-shot recognition flows. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58517-4_36"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Al Machot, F., RElkobaisi, M., and Kyamakya, K. (2020). Zero-shot human activity recognition using non-visual sensors. Sensors, 20.","DOI":"10.3390\/s20030825"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Matsuki, M., Lago, P., and Inoue, S. (2019). Characterizing Word Embeddings for Zero-Shot Sensor-Based Human Activity Recognition. Sensors, 19.","DOI":"10.3390\/s19225043"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ohashi, H., Al-Naser, M., Ahmed, S., Nakamura, K., Sato, T., and Dengle, A. (2018). Attributes\u2019 Importance for Zero-Shot Pose-Classification Based on Wearable Sensors. Sensors, 18.","DOI":"10.3390\/s18082485"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chao, W.L., Changpinyo, S., Gong, B., and Sha, F. (2016, January 8\u201316). An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"ref_25","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. arXiv."},{"key":"ref_26","unstructured":"Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., and Lillicrap, T. (2016, January 19\u201324). Meta-Learning with Memory-Augmented Neural Networks. Proceedings of the 33rd International Conference on Machine Learning (ICML), New York, NY, USA."},{"key":"ref_27","unstructured":"Snell, J., Swersky, K., and Zemel, R.S. (2017, January 4\u20139). Prototypical networks for few-shot learning. Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_28","unstructured":"Jayaraman, D., and Grauman, K. (2014, January 8\u201313). Zero-shot recognition with unreliable attributes. Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS), Montreal, QC, Canada."},{"key":"ref_29","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., and Dean, J. (2013, January 7). Distributed Representations of Words and Phrases and their Compositionality. Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS), Harrahs and Harveys, Lake Tahoe, NV, USA."},{"key":"ref_30","unstructured":"Pennington, J., Socher, R., and Manning, C.D. (, January 25\u201329). Glove: Global vectors for word representation. Proceedings of the Empirical Methods in Natural Language Processing, Doha, Qatar."},{"key":"ref_31","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_32","doi-asserted-by":"crossref","unstructured":"Xie, G.S., Liu, L., Jin, X., Zhu, F., Zhang, Z., Qin, J., Yao, Y., and Shao, L. (2019, January 16\u201320). Attentive region embedding network for zero-shot learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00961"},{"key":"ref_33","unstructured":"Reed, S., Akata, Z., Lee, H., and Schiele, B. (July, January 26). Learning deep representations of fine-grained visual descriptions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ba, J.L., Swersky, K., Fidler, S., and Salakhutdinov, R. (2015, January 7\u201312). Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions. Proceedings of the IEEE International Conference on Computer Vision (CVPR), Boston, MA, USA.","DOI":"10.1109\/ICCV.2015.483"},{"key":"ref_35","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_36","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., and Belongie, S. (2011). The Caltech-Ucsd Birds-200\u20132011 Dataset, California Institute of Technology."},{"key":"ref_37","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 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref_38","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_39","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_40","unstructured":"Changpinyo, S., Chao, W., Gong, B., and Sha, F. (July, January 26). Synthesized Classifiers for Zero-Shot Learning. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_41","unstructured":"Liu, J., Li, X., and Yang, G. (2018, January 3\u20136). Cross-Class Sample Synthesis for Zero-shot Learning. Proceedings of the 29th British Machine Vision Conference (NMVC), Newcastle, UK."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Koniusz, P. (2018, January 18\u201322). Zero-shot kernel learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00800"},{"key":"ref_43","unstructured":"Yang, S.Q., Wang, K., and Herranz, L. (2020). Simple and effective localized attribute representations for zero-shot learning. arXiv."},{"key":"ref_44","unstructured":"Le Cacheux, Y., le Borgne, H., and Crucianu, M. (November, January 27). Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ding, Z., and Liu, H. (2019, January 16\u201320). Marginalized Latent Semantic Encoder for Zero-Shot Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00635"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/9\/3241\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:57:58Z","timestamp":1760162278000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/9\/3241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,7]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21093241"],"URL":"https:\/\/doi.org\/10.3390\/s21093241","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,7]]}}}