{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:26:52Z","timestamp":1776212812881,"version":"3.50.1"},"reference-count":50,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:00:00Z","timestamp":1632873600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001292","name":"Edinburgh Napier University","doi-asserted-by":"publisher","award":["N5155"],"award-info":[{"award-number":["N5155"]}],"id":[{"id":"10.13039\/501100001292","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>This paper proposes a novel approach for semi-supervised domain adaptation for holistic regression tasks, where a DNN predicts a continuous value y\u2208R given an input image x. The current literature generally lacks specific domain adaptation approaches for this task, as most of them mostly focus on classification. In the context of holistic regression, most of the real-world datasets not only exhibit a covariate (or domain) shift, but also a label gap\u2014the target dataset may contain labels not included in the source dataset (and vice versa). We propose an approach tackling both covariate and label gap in a unified training framework. Specifically, a Generative Adversarial Network (GAN) is used to reduce covariate shift, and label gap is mitigated via label normalisation. To avoid overfitting, we propose a stopping criterion that simultaneously takes advantage of the Maximum Mean Discrepancy and the GAN Global Optimality condition. To restore the original label range\u2014that was previously normalised\u2014a handful of annotated images from the target domain are used. Our experimental results, run on 3 different datasets, demonstrate that our approach drastically outperforms the state-of-the-art across the board. Specifically, for the cell counting problem, the mean squared error (MSE) is reduced from 759 to 5.62; in the case of the pedestrian dataset, our approach lowered the MSE from 131 to 1.47. For the last experimental setup, we borrowed a task from plant biology, i.e., counting the number of leaves in a plant, and we ran two series of experiments, showing the MSE is reduced from 2.36 to 0.88 (intra-species), and from 1.48 to 0.6 (inter-species).<\/jats:p>","DOI":"10.3390\/jimaging7100198","type":"journal-article","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T08:27:44Z","timestamp":1632904064000},"page":"198","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4914-174X","authenticated-orcid":false,"given":"Mattia","family":"Litrico","sequence":"first","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Catania, 95125 Catania, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6127-2470","authenticated-orcid":false,"given":"Sebastiano","family":"Battiato","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Catania, 95125 Catania, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8795-9294","authenticated-orcid":false,"given":"Sotirios A.","family":"Tsaftaris","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Edinburgh, Edinburgh EH9 3FG, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5232-677X","authenticated-orcid":false,"given":"Mario Valerio","family":"Giuffrida","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,29]]},"reference":[{"key":"ref_1","unstructured":"Zhao, S., Yue, X., Zhang, S., Li, B., Zhao, H., Wu, B., Krishna, R., Gonzalez, J., Sangiovanni-Vincentelli, A., and Seshia, S. (2020). A Review of Single-Source Deep Unsupervised Visual Domain Adaptation. IEEE Trans. Neural Netw. Learn. Syst., 1\u201321."},{"key":"ref_2","unstructured":"Tachet des Combes, R., Zhao, H., Wang, Y.X., and Gordon, G. (2020). Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift. Neural Information Processing Systems (NeurIPS). arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3071","DOI":"10.1109\/TPAMI.2018.2868685","article-title":"Transferable Representation Learning with Deep Adaptation Networks","volume":"41","author":"Long","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.patrec.2020.06.002","article-title":"SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning","volume":"136","author":"Furnari","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., and Lempitsky, V. (2017). Domain-Adversarial Training of Neural Networks. Domain Adaptation in Computer Vision Applications, Springer.","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref_6","unstructured":"Liu, A.H., Liu, Y.C., Yeh, Y.Y., and Wang, Y.C.F. (2018). A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation. Advances in Neural Information Processing Systems. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., and Darrell, T. (2017, January 22\u201325). Adversarial Discriminative Domain Adaptation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Atapour-Abarghouei, A., and Breckon, T. (2018, January 19\u201321). Real-Time Monocular Depth Estimation Using Synthetic Data with Domain Adaptation via Image Style Transfer. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00296"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3993","DOI":"10.1109\/TIP.2019.2963389","article-title":"Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach","volume":"29","author":"Gholami","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., and Webb, R. (2017, January 22\u201325). Learning from Simulated and Unsupervised Images through Adversarial Training. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhuo, J., Wang, S., Zhang, W., and Huang, Q. (2017, January 23\u201327). Deep Unsupervised Convolutional Domain Adaptation. Proceedings of the 25th ACM International Conference on Multimedia, Mountain View, CA, USA.","DOI":"10.1145\/3123266.3123292"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Busto, P.P., and Gall, J. (2017, January 24\u201327). 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_13","doi-asserted-by":"crossref","unstructured":"Liu, H., Cao, Z., Long, M., Wang, J., and Yang, Q. (2019, January 16\u201320). Separate to Adapt: Open Set Domain Adaptation via Progressive Separation. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00304"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Cao, Z., Long, M., Wang, J., and Jordan, M.I. (2018, January 19\u201321). Partial Transfer Learning with Selective Adversarial Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00288"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cao, Z., Ma, L., Long, M., and Wang, J. (2018, January 8\u201314). Partial Adversarial Domain Adaptation. Proceedings of the Computer Vision\u2014ECCV 2018, Munich, Germany.","DOI":"10.1007\/978-3-030-01237-3_9"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"You, K., Long, M., Cao, Z., Wang, J., and Jordan, M.I. (2019, January 16\u201320). Universal Domain Adaptation. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00283"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dobrescu, A., Giuffrida, M.V., and Tsaftaris, S.A. (2017, January 22\u201329). Leveraging Multiple Datasets for Deep Leaf Counting. Proceedings of the 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), Venice, Italy.","DOI":"10.1109\/ICCVW.2017.243"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Giuffrida, M.V., Dobrescu, A., Doerner, P., and Tsaftaris, S.A. (2019, January 16\u201320). Leaf Counting Without Annotations Using Adversarial Unsupervised Domain Adaptation. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00315"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Puc, A., \u0160truc, V., and Grm, K. (2021, January 18\u201322). Analysis of Race and Gender Bias in Deep Age Estimation Models. Proceedings of the 2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, The Netherlands.","DOI":"10.23919\/Eusipco47968.2020.9287219"},{"key":"ref_20","unstructured":"Kuleshov, V., Fenner, N., and Ermon, S. (2018, January 10\u201315). Accurate uncertainties for deep learning using calibrated regression. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gretton, A., Borgwardt, K., Rasch, M., Sch\u00f6lkopf, B., and Smola, A. (2007). A Kernel Method for the Two-Sample-Problem. Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference, Vancouver, BC, Canada, 4\u20137 December 2007, MIT Press.","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"ref_22","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gopalan, R., Ruonan, L., and Chellappa, R. (2011, January 6\u201313). Domain adaptation for object recognition: An unsupervised approach. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126344"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Luo, Z., Hu, J., Deng, W., and Shen, H. (2018, January 15\u201319). Deep Unsupervised Domain Adaptation for Face Recognition. Proceedings of the 2018 13th IEEE International Conference on Automatic Face Gesture Recognition (FG 2018), Xi\u2019an, China.","DOI":"10.1109\/FG.2018.00073"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Javanmardi, M., and Tasdizen, T. (2018, January 4\u20137). Domain adaptation for biomedical image segmentation using adversarial training. Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.","DOI":"10.1109\/ISBI.2018.8363637"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sun, B., and Saenko, K. (2016, January 11\u201314). Deep CORAL: Correlation Alignment for Deep Domain Adaptation. Proceedings of the European Conference on Computer Vision (ECCV) 2016 Workshops, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Roy, S., Siarohin, A., Sangineto, E., Bulo, S.R., Sebe, N., and Ricci, E. (2019, January 16\u201320). Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00970"},{"key":"ref_28","unstructured":"Kundu, J.N., Venkat, N., Rahul, M.V., and Babu, R.V. (2020, January 14\u201319). Universal Source-Free Domain Adaptation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Dong, N., Kampffmeyer, M., Liang, X., Wang, Z., Dai, W., and Xing, E. (2018, January 16\u201320). Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, Granada, Spain.","DOI":"10.1007\/978-3-030-00934-2_61"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hossain, M.A., Reddy, M.K.K., Cannons, K., Xu, Z., and Wang, Y. (2020, January 13\u201315). Domain Adaptation in Crowd Counting. Proceedings of the 2020 17th Conference on Computer and Robot Vision (CRV), Ottawa, ON, Canada.","DOI":"10.1109\/CRV50864.2020.00028"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2017.07.007","article-title":"A survey of recent advances in CNN-based single image crowd counting and density estimation","volume":"107","author":"Sindagi","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kuhnke, F., and Ostermann, J. (November, January 27). Deep Head Pose Estimation Using Synthetic Images and Partial Adversarial Domain Adaption for Continuous Label Spaces. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.01026"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Takahashi, R., Hashimoto, A., Sonogashira, M., and Iiyama, M. (2020, January 23\u201328). Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift. Proceedings of the European Conference on Computer Vision\u2014ECCV 2020, Virtual.","DOI":"10.1007\/978-3-030-58517-4_1"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_35","unstructured":"Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., and Garnett, R. (2016). f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., and Smolley, S.P. (2017, January 24\u201327). Least Squares Generative Adversarial Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref_37","unstructured":"Razavi, A., Oord, A.V.D., Poole, B., and Vinyals, O. (2019, January 6\u20139). Preventing Posterior Collapse with delta-VAEs. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_38","first-page":"723","article-title":"A Kernel Two-Sample Test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32, Curran Associates, Inc."},{"key":"ref_40","first-page":"1324","article-title":"Learning to count objects in images","volume":"23","author":"Lempitsky","year":"2010","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1109\/TMI.2007.896925","article-title":"Computational Framework for Simulating Fluorescence Microscope Images With Cell Populations","volume":"26","author":"Lehmussola","year":"2007","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"2160","DOI":"10.1109\/TIP.2011.2172800","article-title":"Counting People With Low-Level Features and Bayesian Regression","volume":"21","author":"Chan","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ref_43","unstructured":"Bell, J., and Dee, H.M. (2021, August 28). Aberystwyth Leaf Evaluation Dataset. Zenodo. Available online: https:\/\/zenodo.org\/record\/168158."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.patrec.2015.10.013","article-title":"Finely-grained annotated datasets for image-based plant phenotyping","volume":"81","author":"Minervini","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1007\/s00138-015-0734-6","article-title":"Multi-modality Imagery Database for Plant Phenotyping","volume":"27","author":"Cruz","year":"2016","journal-title":"Mach. Vis. Appl."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Uchiyama, H., Sakurai, S., Mishima, M., Arita, D., Okayasu, T., Shimada, A., and Taniguchi, R. (2017, January 24\u201327). An Easy-to-Setup 3D Phenotyping Platform for KOMATSUNA Dataset. Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy.","DOI":"10.1109\/ICCVW.2017.239"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1111\/tpj.14064","article-title":"Pheno-Deep Counter: A unified and versatile deep learning architecture for leaf counting","volume":"96","author":"Giuffrida","year":"2018","journal-title":"Plant J."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1007\/s00138-015-0737-3","article-title":"Leaf segmentation in plant phenotyping: A collation study","volume":"27","author":"Scharr","year":"2016","journal-title":"Mach. Vis. Appl."},{"key":"ref_49","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 7\u20139). Wasserstein Generative Adversarial Networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_50","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Improved Training of Wasserstein GANs. Advances in Neural Information Processing Systems, Curran Associates, Inc."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/10\/198\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:07:18Z","timestamp":1760166438000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/10\/198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,29]]},"references-count":50,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["jimaging7100198"],"URL":"https:\/\/doi.org\/10.3390\/jimaging7100198","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,29]]}}}