{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T21:21:07Z","timestamp":1790716867436,"version":"4.1.0"},"reference-count":45,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2019,5,8]],"date-time":"2019-05-08T00:00:00Z","timestamp":1557273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Domain adaptation is a sub-field of transfer learning that aims at bridging the dissimilarity gap between different domains by transferring and re-using the knowledge obtained in the source domain to the target domain. Many methods have been proposed to resolve this problem, using techniques such as generative adversarial networks (GAN), but the complexity of such methods makes it hard to use them in different problems, as fine-tuning such networks is usually a time-consuming task. In this paper, we propose a method for unsupervised domain adaptation that is both simple and effective. Our model (referred to as TripNet) harnesses the idea of a discriminator and Linear Discriminant Analysis (LDA) to push the encoder to generate domain-invariant features that are category-informative. At the same time, pseudo-labelling is used for the target data to train the classifier and to bring the same classes from both domains together. We evaluate TripNet against several existing, state-of-the-art methods on three image classification tasks: Digit classification (MNIST, SVHN, and USPC datasets), object recognition (Office31 dataset), and traffic sign recognition (GTSRB and Synthetic Signs datasets). Our experimental results demonstrate that (i) TripNet beats almost all existing methods (having a similar simple model like it) on all of these tasks; and (ii) for models that are significantly more complex (or hard to train) than TripNet, it even beats their performance in some cases. Hence, the results confirm the effectiveness of using TripNet for unsupervised domain adaptation in image classification.<\/jats:p>","DOI":"10.3390\/a12050096","type":"journal-article","created":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T11:22:35Z","timestamp":1557400955000},"page":"96","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Triplet Loss Network for Unsupervised Domain Adaptation"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1527-4314","authenticated-orcid":false,"given":"Imad Eddine Ibrahim","family":"Bekkouch","sequence":"first","affiliation":[{"name":"Machine Learning and Knowledge Representation Lab in the Institute of Data Science &amp; AI, Innopolis University, Innopolis 420500, Republic of Tatarstan, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youssef","family":"Youssry","sequence":"additional","affiliation":[{"name":"Machine Learning and Knowledge Representation Lab in the Institute of Data Science &amp; AI, Innopolis University, Innopolis 420500, Republic of Tatarstan, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rustam","family":"Gafarov","sequence":"additional","affiliation":[{"name":"Machine Learning and Knowledge Representation Lab in the Institute of Data Science &amp; AI, Innopolis University, Innopolis 420500, Republic of Tatarstan, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adil","family":"Khan","sequence":"additional","affiliation":[{"name":"Machine Learning and Knowledge Representation Lab in the Institute of Data Science &amp; AI, Innopolis University, Innopolis 420500, Republic of Tatarstan, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asad Masood","family":"Khattak","sequence":"additional","affiliation":[{"name":"College of Technological Innovations, Zayed University, Abu Dhabi 144534, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,5,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_2","unstructured":"Hoffman, J., Tzeng, E., Park, T., Zhu, J.Y., Isola, P., Saenko, K., Efros, A.A., and Darrell, T. (2018, January 10\u201315). CyCADA: Cycle-Consistent Adversarial Domain Adaptation. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Saito, K., Yamamoto, S., Ushiku, Y., and Harada, T. (2018). Open Set Domain Adaptation by Backpropagation. arXiv.","DOI":"10.1007\/978-3-030-01228-1_10"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Busto, P.P., and Gall, J. (2017, January 22\u201329). Open Set Domain Adaptation. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.88"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Motiian, S., Piccirilli, M., Adjeroh, D.A., and Doretto, G. (2017). Unified Deep Supervised Domain Adaptation and Generalization. arXiv.","DOI":"10.1109\/ICCV.2017.609"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Ngo, C., Li, H., and Mei, T. (2015, January 7\u201312). Semi-supervised Domain Adaptation with Subspace Learning for visual recognition. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298826"},{"key":"ref_7","unstructured":"Cai, G., Wang, Y., Zhou, M., and He, L. (2018). Unsupervised Domain Adaptation with Adversarial Residual Transform Networks. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Russo, P., Carlucci, F.M., Tommasi, T., and Caputo, B. (2017). From source to target and back: Symmetric bi-directional adaptive GAN. arXiv.","DOI":"10.1109\/CVPR.2018.00845"},{"key":"ref_9","unstructured":"Deshmukh, A.A., Bansal, A., and Rastogi, A. (2018). Domain2Vec: Deep Domain Generalization. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, Z., Ko, B., and Choi, H. (2018, January 15\u201317). Pseudo-Labeling Using Gaussian Process for Semi-Supervised Deep Learning. Proceedings of the 2018 IEEE International Conference on Big Data and Smart Computing (BigComp), Shanghai, China.","DOI":"10.1109\/BigComp.2018.00046"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ren, Z., and Lee, Y.J. (2018, January 18\u201323). Cross-Domain Self-Supervised Multi-task Feature Learning Using Synthetic Imagery. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00086"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hu, L., Kan, M., Shan, S., and Chen, X. (2018, January 18\u201323). Duplex Generative Adversarial Network for Unsupervised Domain Adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00162"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Pinheiro, P.O. (2017). Unsupervised Domain Adaptation with Similarity Learning. arXiv.","DOI":"10.1109\/CVPR.2018.00835"},{"key":"ref_14","first-page":"5423","article-title":"Learning Semantic Representations for Unsupervised Domain Adaptation","volume":"Volume 80","author":"Dy","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Teng, Y., Choromanska, A., and Bojarski, M. (2018). Invertible Autoencoder for domain adaptation. arXiv.","DOI":"10.3390\/computation7020020"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kan, M., Shan, S., and Chen, X. (2015, January 7\u201313). Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.438"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1109\/TIP.2017.2781422","article-title":"Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval","volume":"27","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wei, J., Liang, J., He, R., and Yang, J. (2018, January 23\u201327). Learning Discriminative Geodesic Flow Kernel for Unsupervised Domain Adaptation. Proceedings of the 2018 IEEE International Conference on Multimedia and Expo (ICME), San Diego, CA, USA.","DOI":"10.1109\/ICME.2018.8486446"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhu, J., Park, T., Isola, P., and Efros, A.A. (2017). Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. arXiv.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_20","unstructured":"Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., and Garnett, R. (2016). Learning Transferrable Representations for Unsupervised Domain Adaptation. Advances in Neural Information Processing Systems 29, Curran Associates, Inc."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., and Kim, K. (2018, January 18\u201323). Image to Image Translation for Domain Adaptation. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00473"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, Z., Yang, M., and Yuan, J. (2018, January 18\u201323). Conditional Generative Adversarial Network for Structured Domain Adaptation. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00145"},{"key":"ref_23","unstructured":"Almahairi, A., Rajeswar, S., Sordoni, A., Bachman, P., and Courville, A.C. (2018). Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lv, F., Zhu, J., Yang, G., and Duan, L. (2019). TarGAN: Generating target data with class labels for unsupervised domain adaptation. Knowl.-Based Syst.","DOI":"10.1016\/j.knosys.2019.02.015"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sankaranarayanan, S., Balaji, Y., Castillo, C.D., and Chellappa, R. (2017). Generate To Adapt: Aligning Domains using Generative Adversarial Networks. arXiv.","DOI":"10.1109\/CVPR.2018.00887"},{"key":"ref_26","unstructured":"Chen, M., Weinberger, K.Q., and Blitzer, J.C. (2011, January 12\u201315). Co-training for Domain Adaptation. Proceedings of the 24th International Conference on Neural Information Processing Systems, Granada, Spain."},{"key":"ref_27","unstructured":"Saito, K., Ushiku, Y., and Harada, T. (2017). Asymmetric Tri-training for Unsupervised Domain Adaptation. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/TITB.2010.2051955","article-title":"A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer","volume":"14","author":"Khan","year":"2010","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., and Harada, T. (2017). Maximum Classifier Discrepancy for Unsupervised Domain Adaptation. arXiv.","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref_30","first-page":"1","article-title":"Domain-Adversarial Training of Neural Networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","unstructured":"Ganin, Y., and Lempitsky, V. (2014). Unsupervised domain adaptation by backpropagation. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., and Darrell, T. (2017). Adversarial Discriminative Domain Adaptation. arXiv.","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref_33","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., and Erhan, D. (2016). Domain Separation Networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., and Li, W. (2016). Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation. arXiv.","DOI":"10.1007\/978-3-319-46493-0_36"},{"key":"ref_35","unstructured":"Liu, M., and Tuzel, O. (2016). Coupled Generative Adversarial Networks. arXiv."},{"key":"ref_36","unstructured":"Liu, M., Breuel, T., and Kautz, J. (2017). Unsupervised Image-to-Image Translation Networks. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., and Krishnan, D. (2016). Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. arXiv.","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_39","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., and Ng, A.Y. (2019, May 02). Reading Digits in Natural Images with Unsupervised Feature Learning. Available online: http:\/\/ufldl.stanford.edu\/housenumbers\/nips2011_housenumbers.pdf."},{"key":"ref_40","unstructured":"Touretzky, D.S. (1989). Neural Network Recognizer for Hand-Written Zip Code Digits. Advances in Neural Information Processing Systems 1, Morgan-Kaufmann."},{"key":"ref_41","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Saenko, K., Kulis, B., Fritz, M., and Darrell, T. (2010). Adapting Visual Category Models to New Domains. Proceedings of the 11th European Conference on Computer Vision: Part IV, Springer.","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref_43","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the 25th International Conference on Neural Information Processing Systems\u2013Volume 1, Lake Tahoe, NV, USA."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_45","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"Volume 9","author":"Teh","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/12\/5\/96\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:50:00Z","timestamp":1760187000000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/12\/5\/96"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,8]]},"references-count":45,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2019,5]]}},"alternative-id":["a12050096"],"URL":"https:\/\/doi.org\/10.3390\/a12050096","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,8]]}}}