{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:18:28Z","timestamp":1767705508539,"version":"build-2065373602"},"reference-count":38,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T00:00:00Z","timestamp":1760745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan","award":["BR24992852"],"award-info":[{"award-number":["BR24992852"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>This paper presents a systematic framework that combines federated learning, self-supervised learning, and few-shot learning paradigms for privacy-preserving face recognition. We use the large-scale CASIA-WebFace dataset for self-supervised pre-training using SimCLR in a federated setting, followed by federated few-shot fine-tuning on the LFW dataset using prototypical networks. Through comprehensive evaluation across six state-of-the-art architectures (ResNet, DenseNet, MobileViT, ViT-Small, CvT, and CoAtNet), we demonstrate that while our federated approach successfully preserves data privacy, it comes with significant performance trade-offs. Our results show 12\u201330% accuracy degradation compared to centralized methods, representing the substantial cost of privacy preservation. We find that traditional CNNs show superior robustness to federated constraints compared to transformer-based architectures, and that five-shot configurations provide an optimal balance between data efficiency and performance. This work provides important empirical insights and establishes benchmarks for federated few-shot face recognition, quantifying the privacy\u2013utility trade-offs that practitioners must consider when deploying such systems in real-world applications.<\/jats:p>","DOI":"10.3390\/jimaging11100370","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:44:10Z","timestamp":1760957050000},"page":"370","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Federated Self-Supervised Few-Shot Face Recognition"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7655-8391","authenticated-orcid":false,"given":"Nursultan","family":"Makhanov","sequence":"first","affiliation":[{"name":"Smart City Research Center, Astana IT University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0355-5856","authenticated-orcid":false,"given":"Beibut","family":"Amirgaliyev","sequence":"additional","affiliation":[{"name":"Smart City Research Center, Astana IT University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7891-242X","authenticated-orcid":false,"given":"Talgat","family":"Islamgozhayev","sequence":"additional","affiliation":[{"name":"Smart City Research Center, Astana IT University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6343-5277","authenticated-orcid":false,"given":"Didar","family":"Yedilkhan","sequence":"additional","affiliation":[{"name":"Smart City Research Center, Astana IT University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.54254\/2755-2721\/80\/2024CH0053","article-title":"A Review of Traditional Methods and Deep Learning for Face Recognition","volume":"80","author":"Zeng","year":"2024","journal-title":"Appl. Comput. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Salagean, G.L., and Leba, M. (2023). Face Recognition: A Literature Review. Seventh International Scientific Conference ITEMA\u2014Recent Advances in Information Technology, Tourism, Economics, Management and Agriculture, Udru\u017eenje ekonomista i menad\u017eera Balkana.","DOI":"10.31410\/ITEMA.2023.55"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., and Zhang, L. (2021, January 11\u201317). Cvt: Introducing convolutions to vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mane, S.B., Shah, N., Garje, V., and Tejwani, A. (2024, January 23\u201324). A Comprehensive Survey of Face Recognition Advancements. Proceedings of the 2024 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA), Pune, India.","DOI":"10.1109\/ICCUBEA61740.2024.10774962"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"191","DOI":"10.54097\/hset.v24i.3921","article-title":"A Survey of Face Recognition Methods based on Deep Learning","volume":"24","author":"Chen","year":"2022","journal-title":"Highlights Sci. Eng. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"39603","DOI":"10.1109\/ACCESS.2024.3373691","article-title":"Maintaining Privacy in Face Recognition Using Federated Learning Method","volume":"12","author":"Woubie","year":"2024","journal-title":"IEEE Access"},{"key":"ref_10","unstructured":"Solomon, E., and Woubie, A. (2024). Federated Learning Method for Preserving Privacy in Face Recognition System. arXiv."},{"key":"ref_11","unstructured":"Kim, H., Choi, H., and Kwak, Y. (2024). Federated Learning for Face Recognition via Intra-subject Self-supervised Learning. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"104","DOI":"10.54254\/2755-2721\/81\/20241078","article-title":"A Comprehensive Analysis of Face Recognition Based on Advanced Deep Learning Technology","volume":"81","author":"Xie","year":"2024","journal-title":"Appl. Comput. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Taherdoost, H. (2024). Beyond Supervised: The Rise of Self-Supervised Learning in Autonomous Systems. Information, 15.","DOI":"10.3390\/info15080491"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lin, C.H., and Wu, B.F. (2021, January 19\u201322). Domain Adapting Ability Of Self-Supervised Learning For Face Recognition. Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA.","DOI":"10.1109\/ICIP42928.2021.9506677"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Aghaomidi, P., Aram, S., and Bahmani, Z. (December, January 30). Leveraging Self-Supervised Learning for Accurate Facial Keypoint Detection in Thermal Images. Proceedings of the 2023 30th National and 8th International Iranian Conference on Biomedical Engineering (ICBME), Tehran, Iran.","DOI":"10.1109\/ICBME61513.2023.10488499"},{"key":"ref_16","unstructured":"Tsoumplekas, G., Li, V., Sarigiannidis, P., and Argyriou, V. (2025). A Complete Survey on Contemporary Methods, Emerging Paradigms and Hybrid Approaches for Few-Shot Learning. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s13735-023-00279-4","article-title":"Few-shot and meta-learning methods for image understanding: A survey","volume":"12","author":"He","year":"2023","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1364\/JOSAA.31.000001","article-title":"Self-training-based face recognition using semi-supervised linear discriminant analysis and affinity propagation","volume":"31","author":"Gan","year":"2013","journal-title":"J. Opt. Soc. Am. A"},{"key":"ref_19","unstructured":"Snell, J., Swersky, K., and Zemel, R.S. (2017). Prototypical Networks for Few-shot Learning. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chanda, S., AsishChakrapani, G., Brun, A., Hast, A., Pal, U., and Doermann, D.S. (2019, January 26\u201329). Face Recognition\u2014A One-Shot Learning Perspective. Proceedings of the 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Sorrento, Italy.","DOI":"10.1109\/SITIS.2019.00029"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Albayati, A.M., Chtourou, W., and Zarai, F. (2022, January 20\u201322). Attending to Channels in One-Shot Learning Face Recognition using Squeeze-and-Excitation Networks. Proceedings of the 2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Ankara, Turkey.","DOI":"10.1109\/ISMSIT56059.2022.9932722"},{"key":"ref_22","first-page":"43","article-title":"k-Shot Learning for Face Recognition","volume":"181","author":"Ranadive","year":"2018","journal-title":"Int. J. Comput. Appl."},{"key":"ref_23","unstructured":"Yi, D., Lei, Z., Liao, S., and Li, S.Z. (2014). Learning face representation from scratch. arXiv."},{"key":"ref_24","unstructured":"Huang, G.B., Mattar, M., Berg, T., and Learned-Miller, E. (2008, January 12\u201318). Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. Proceedings of the Workshop on Faces in \u2018Real-Life\u2019 Images: Detection, Alignment, and Recognition, Marseille, France."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ewerth, R., M\u00fchling, M., and Freisleben, B. (2006, January 11\u201313). Self-Supervised Learning of Face Appearances in TV Casts and Movies. Proceedings of the Eighth IEEE International Symposium on Multimedia (ISM\u201906), San Diego, CA, USA.","DOI":"10.1109\/ISM.2006.136"},{"key":"ref_26","unstructured":"Khan, A., Asmatullah, L., Malik, A., Khan, S., and Asif, H. (2025). A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xiao, J., Zhu, G., and Loianno, G. (2024). VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization. arXiv.","DOI":"10.1109\/WACV61041.2025.00649"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lialin, V., Rawls, S., Chan, D., Ghosh, S., Rumshisky, A., and Hamza, W. (2023, January 3\u20137). Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data. Proceedings of the 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Waikoloa, HI, USA.","DOI":"10.1109\/WACVW58289.2023.00043"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhao, X., Evans, N.W.D., and Dugelay, J.L. (2011, January 11\u201314). Semi-supervised face recognition with LDA self-training. Proceedings of the 2011 18th IEEE International Conference on Image Processing, Brussels, Belgium.","DOI":"10.1109\/ICIP.2011.6116305"},{"key":"ref_30","unstructured":"and Kumar, S. (2024, January 3\u20134). Advancements in Meta-Learning Paradigms: A Comprehensive Exploration of Techniques for Few-Shot Learning in Computer Vision. Proceedings of the 2024 International Conference on Intelligent Systems for Cybersecurity (ISCS), Gurugram, India."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Gharoun, H., Momenifar, F., Chen, F., and Gandomi, A.H. (2023). Meta-learning approaches for few-shot learning: A survey of recent advances. arXiv.","DOI":"10.1145\/3659943"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Xu, N., and Feng, W. (2023, January 28\u201330). MetaFake: Few-shot Face Forgery Detection with Meta Learning. Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security, Chicago, IL, USA.","DOI":"10.1145\/3577163.3595108"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Althnian, A., Aloboud, N., Alkharashi, N., Alduwaish, F., Alrshoud, M., and Kurdi, H.A. (2020). Face Gender Recognition in the Wild: An Extensive Performance Comparison of Deep-Learned, Hand-Crafted, and Fused Features with Deep and Traditional Models. Appl. Sci., 11.","DOI":"10.3390\/app11010089"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, S., Su, N., and Li, B. (2024, January 23\u201326). Calibre: Towards fair and accurate personalized federated learning with self-supervised learning. Proceedings of the 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS), Jersey City, NJ, USA.","DOI":"10.1109\/ICDCS60910.2024.00087"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1504\/IJKESDP.2019.103896","article-title":"Learning combined features for automatic facial expression recognition","volume":"6","author":"Zrira","year":"2019","journal-title":"Int. J. Knowl. Eng. Soft Data Paradig."},{"key":"ref_36","first-page":"70","article-title":"Face recognition using combined binary particle swarm optimisation and hidden layer of artificial neural network","volume":"14","author":"Charan","year":"2019","journal-title":"Int. J. Adv. Intell. Paradig."},{"key":"ref_37","unstructured":"Mehta, S., and Rastegari, M. (2021). Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv."},{"key":"ref_38","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/370\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T11:30:53Z","timestamp":1760959853000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/370"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,18]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jimaging11100370"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11100370","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,18]]}}}