{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:56:52Z","timestamp":1781193412450,"version":"3.54.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"26","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["13N16336"],"award-info":[{"award-number":["13N16336"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["AL 638\/15-1"],"award-info":[{"award-number":["AL 638\/15-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["Al 638\/14-1"],"award-info":[{"award-number":["Al 638\/14-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["Al 638\/13-1"],"award-info":[{"award-number":["Al 638\/13-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012320","name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012320","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep feature learning has become crucial in large-scale face recognition, and margin-based loss functions have demonstrated impressive success in this field. These methods aim to enhance the discriminative power of the softmax loss by increasing the feature margin between different classes. These methods assume class balance, where a fixed margin is sufficient to squeeze intra-class variation equally. However, real-face datasets often exhibit imbalanced classes, where the fixed margin is suboptimal, limiting the discriminative power and generalizability of the face recognition model. Furthermore, margin-based approaches typically focus on enhancing discrimination either in the angle or cosine space, emphasizing one boundary while disregarding the other. To overcome these limitations, we propose a joint adaptive margins loss function (JAMsFace) that learns class-related margins for both angular and cosine spaces. This approach allows adaptive margin penalties to adjust adaptively for different classes. We explain and analyze the proposed JAMsFace geometrically and present comprehensive experiments on multiple face recognition benchmarks. The results show that JAMsFace outperforms existing face recognition losses in mainstream face recognition tasks. Specifically, JAMsFace advances the state-of-the-art face recognition performance on LFW, CPLFW, and CFP-FP and achieves comparable results on CALFW and AgeDB-30. Furthermore, for the challenging IJB-B and IJB-C benchmarks, JAMsFace achieves impressive true acceptance rates (TARs) of 89.09% and 91.81% at a false acceptance rate (FAR) of 1e-4, respectively.<\/jats:p>","DOI":"10.1007\/s00521-023-08732-5","type":"journal-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T15:02:36Z","timestamp":1686927756000},"page":"19025-19037","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["JAMsFace: joint adaptive margins loss for deep face recognition"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9179-6061","authenticated-orcid":false,"given":"Aly","family":"Khalifa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayoub","family":"Al-Hamadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"key":"8732_CR1","doi-asserted-by":"crossref","unstructured":"Boutros F, Damer N, Kirchbuchner F, et\u00a0al (2022) Elasticface: elastic margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 1578\u20131587","DOI":"10.1109\/CVPRW56347.2022.00164"},{"key":"8732_CR2","doi-asserted-by":"crossref","unstructured":"Cao Q, Shen L, Xie W, et\u00a0al (2018) Vggface2: a dataset for recognising faces across pose and age. In: 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), IEEE, p 67\u201374","DOI":"10.1109\/FG.2018.00020"},{"key":"8732_CR3","doi-asserted-by":"crossref","unstructured":"Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), IEEE, p 539\u2013546","DOI":"10.1109\/CVPR.2005.202"},{"key":"8732_CR4","doi-asserted-by":"crossref","unstructured":"Deng J, Zhou Y, Zafeiriou S (2017) Marginal loss for deep face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, p 60\u201368","DOI":"10.1109\/CVPRW.2017.251"},{"key":"8732_CR5","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Xue N, et\u00a0al (2019) Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 4690\u20134699","DOI":"10.1109\/CVPR.2019.00482"},{"key":"8732_CR6","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Liu T, et\u00a0al (2020) Sub-center arcface: boosting face recognition by large-scale noisy web faces. In: European conference on computer vision, Springer, p 741\u2013757","DOI":"10.1007\/978-3-030-58621-8_43"},{"key":"8732_CR7","doi-asserted-by":"crossref","unstructured":"Guillaumin M, Verbeek J, Schmid C (2009) Is that you? metric learning approaches for face identification. In: IEEE 12th international conference on computer vision, IEEE, p 498\u2013505","DOI":"10.1109\/ICCV.2009.5459197"},{"key":"8732_CR8","doi-asserted-by":"crossref","unstructured":"Guo Y, Zhang L, Hu Y, et\u00a0al (2016) Ms-celeb-1m: a dataset and benchmark for large-scale face recognition. In: European conference on computer vision, Springer, p 87\u2013102","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"8732_CR9","doi-asserted-by":"crossref","unstructured":"He L, Wang Z, Li Y, et\u00a0al (2020) Softmax dissection: towards understanding intra-and inter-class objective for embedding learning. In: Proceedings of the AAAI conference on artificial intelligence, p 10957\u201310964","DOI":"10.1609\/aaai.v34i07.6729"},{"key":"8732_CR10","unstructured":"Huang GB, Mattar M, Berg T, et\u00a0al (2008) Labeled faces in the wild: a database forstudying face recognition in unconstrained environments. In: Workshop on faces in\u2019Real-Life\u2019Images: detection, alignment, and recognition"},{"key":"8732_CR11","doi-asserted-by":"crossref","unstructured":"Huang Y, Wang Y, Tai Y, et\u00a0al (2020) Curricularface: adaptive curriculum learning loss for deep face recognition. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 5901\u20135910","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"8732_CR12","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2020.0111152","author":"NS Irjanto","year":"2020","unstructured":"Irjanto NS, Surantha N (2020) Home security system with face recognition based on convolutional neural network. Int J Adv Comput Sci Appl. https:\/\/doi.org\/10.14569\/IJACSA.2020.0111152","journal-title":"Int J Adv Comput Sci Appl"},{"issue":"17","key":"8732_CR13","doi-asserted-by":"publisher","first-page":"25741","DOI":"10.1007\/s11042-021-10865-5","volume":"80","author":"J Jiao","year":"2021","unstructured":"Jiao J, Liu W, Mo Y et al (2021) Dyn-arcface: dynamic additive angular margin loss for deep face recognition. Multimed Tools Appl 80(17):25741\u201325756","journal-title":"Multimed Tools Appl"},{"key":"8732_CR14","first-page":"122","volume-title":"A systems engineering approach to realizing synergistic capabilities, engineering artificially intelligent systems","author":"M Johnson","year":"2021","unstructured":"Johnson M, Bradshaw JM (2021) How interdependence explains the world of teamwork. A systems engineering approach to realizing synergistic capabilities, engineering artificially intelligent systems. Springer, Cham, pp 122\u2013146"},{"key":"8732_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10723-018-9467-x","volume":"17","author":"H Kavalionak","year":"2019","unstructured":"Kavalionak H, Gennaro C, Amato G et al (2019) Distributed video surveillance using smart cameras. J Grid Comput 17:59\u201377","journal-title":"J Grid Comput"},{"key":"8732_CR16","doi-asserted-by":"crossref","unstructured":"Khalifa A, Al-Hamadi A (2021) A survey on loss functions for deep face recognition network. In: 2021 IEEE 2nd International conference on human-machine systems (ICHMS), IEEE, p 1\u20137","DOI":"10.1109\/ICHMS53169.2021.9582652"},{"issue":"11","key":"8732_CR17","doi-asserted-by":"publisher","first-page":"5568","DOI":"10.3390\/app12115568","volume":"12","author":"A Khalifa","year":"2022","unstructured":"Khalifa A, Abdelrahman AA, Strazdas D et al (2022) Face recognition and tracking framework for human-robot interaction. Appl Sci 12(11):5568","journal-title":"Appl Sci"},{"key":"8732_CR18","doi-asserted-by":"crossref","unstructured":"Kim M, Jain AK, Liu X (2022) Adaface: quality adaptive margin for face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 18750\u201318759","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"8732_CR19","doi-asserted-by":"crossref","unstructured":"Liu B, Deng W, Zhong Y, et\u00a0al (2019a) Fair loss: margin-aware reinforcement learning for deep face recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, p 10052\u201310061","DOI":"10.1109\/ICCV.2019.01015"},{"key":"8732_CR20","doi-asserted-by":"crossref","unstructured":"Liu H, Zhu X, Lei Z, et\u00a0al (2019b) Adaptiveface: adaptive margin and sampling for face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 11947\u201311956","DOI":"10.1109\/CVPR.2019.01222"},{"key":"8732_CR21","unstructured":"Liu W, Wen Y, Yu Z, et\u00a0al (2016) Large-margin softmax loss for convolutional neural networks. In: Proceedings of the 33rd international conference on international conference on machine learning-vol 48, p 507\u2013516"},{"key":"8732_CR22","doi-asserted-by":"crossref","unstructured":"Liu W, Wen Y, Yu Z, et\u00a0al (2017) Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 212\u2013220","DOI":"10.1109\/CVPR.2017.713"},{"key":"8732_CR23","doi-asserted-by":"crossref","unstructured":"Maze B, Adams J, Duncan JA, et\u00a0al (2018) Iarpa janus benchmark-c: face dataset and protocol. In: 2018 International conference on biometrics (ICB), IEEE, p 158\u2013165","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"8732_CR24","doi-asserted-by":"crossref","unstructured":"Moschoglou S, Papaioannou A, Sagonas C, et\u00a0al (2017) Agedb: the first manually collected, in-the-wild age database. In: proceedings of the IEEE conference on computer vision and pattern recognition workshops, p 51\u201359","DOI":"10.1109\/CVPRW.2017.250"},{"key":"8732_CR25","unstructured":"Oinar C, Le BM, Woo SS (2022) Kappaface: adaptive additive angular margin loss for deep face recognition. arXiv preprint arXiv:2201.07394"},{"key":"8732_CR26","doi-asserted-by":"crossref","unstructured":"Parkhi OM, Vedaldi A, Zisserman A (2015) Deep face recognition","DOI":"10.5244\/C.29.41"},{"key":"8732_CR27","unstructured":"Paszke A, Gross S, Massa F, et\u00a0al (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, vol 32"},{"key":"8732_CR28","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"8732_CR29","doi-asserted-by":"crossref","unstructured":"Seal A, Bhattacharjee D, Nasipuri M, et\u00a0al (2012) Minutiae from bit-plane sliced thermal images for human face recognition. In: Proceedings of the international conference on soft computing for problem solving (SocProS 2011), Springer, p 113\u2013124","DOI":"10.1007\/978-81-322-0491-6_11"},{"key":"8732_CR30","doi-asserted-by":"crossref","unstructured":"Seal A, Bhattacharjee D, Nasipuri M, et\u00a0al (2013a) Thermal human face recognition based on gappypca. In: 2013 IEEE 2nd international conference on image information processing (ICIIP-2013), IEEE, p 597\u2013600","DOI":"10.1109\/ICIIP.2013.6707662"},{"key":"8732_CR31","doi-asserted-by":"crossref","unstructured":"Seal A, Ganguly S, Bhattacharjee D, et\u00a0al (2013b) Thermal human face recognition based on haar wavelet transform and series matching technique. In: Multimedia processing, communication and computing applications: proceedings of the 1st international conference, ICMCCA, Springer, p 155\u2013167","DOI":"10.1007\/978-81-322-1143-3_13"},{"key":"8732_CR32","doi-asserted-by":"crossref","unstructured":"Sengupta S, Chen JC, Castillo C, et\u00a0al (2016) Frontal to profile face verification in the wild. In: 2016 IEEE winter conference on applications of computer vision (WACV), IEEE, p 1\u20139","DOI":"10.1109\/WACV.2016.7477558"},{"key":"8732_CR33","unstructured":"Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. In: Advances in neural information processing systems, vol 29"},{"key":"8732_CR34","doi-asserted-by":"crossref","unstructured":"Wang F, Xiang X, Cheng J, et\u00a0al (2017) Normface: L2 hypersphere embedding for face verification. In: Proceedings of the 25th ACM international conference on multimedia, p 1041\u20131049","DOI":"10.1145\/3123266.3123359"},{"key":"8732_CR35","doi-asserted-by":"crossref","unstructured":"Wang H, Wang Y, Zhou Z, et\u00a0al (2018) Cosface: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 5265\u20135274","DOI":"10.1109\/CVPR.2018.00552"},{"key":"8732_CR36","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.neucom.2020.10.081","volume":"429","author":"M Wang","year":"2021","unstructured":"Wang M, Deng W (2021) Deep face recognition: a survey. Neurocomputing 429:215\u2013244","journal-title":"Neurocomputing"},{"key":"8732_CR37","doi-asserted-by":"crossref","unstructured":"Wen Y, Zhang K, Li Z, et\u00a0al (2016) A discriminative feature learning approach for deep face recognition. In: European conference on computer vision, Springer, p 499\u2013515","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"8732_CR38","unstructured":"Wen Y, Liu W, Weller A, et\u00a0al (2022) Sphereface2: binary classification is all you need for deep face recognition. In: International conference on learning representations"},{"key":"8732_CR39","doi-asserted-by":"crossref","unstructured":"Whitelam C, Taborsky E, Blanton A, et\u00a0al (2017) Iarpa janus benchmark-b face dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, p 90\u201398","DOI":"10.1109\/CVPRW.2017.87"},{"key":"8732_CR40","unstructured":"Xie W, Zisserman A (2018) Multicolumn networks for face recognition. arXiv preprint arXiv:1807.09192"},{"key":"8732_CR41","doi-asserted-by":"crossref","unstructured":"Xie W, Shen L, Zisserman A (2018) Comparator networks. In: Proceedings of the European conference on computer vision (ECCV), p 782\u2013797","DOI":"10.1007\/978-3-030-01252-6_48"},{"key":"8732_CR42","unstructured":"Yi D, Lei Z, Liao S, et\u00a0al (2014) Learning face representation from scratch. arXiv preprint arXiv:1411.7923"},{"issue":"10","key":"8732_CR43","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang K, Zhang Z, Li Z et al (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499\u20131503","journal-title":"IEEE Signal Process Lett"},{"key":"8732_CR44","first-page":"7","volume":"5","author":"T Zheng","year":"2018","unstructured":"Zheng T, Deng W (2018) Cross-pose lfw: a database for studying cross-pose face recognition in unconstrained environments. Beijing Univ Posts Telecommun Tech Rep 5:7","journal-title":"Beijing Univ Posts Telecommun Tech Rep"},{"key":"8732_CR45","unstructured":"Zheng T, Deng W, Hu J (2017) Cross-age lfw: a database for studying cross-age face recognition in unconstrained environments. arXiv preprint arXiv:1708.08197"},{"key":"8732_CR46","doi-asserted-by":"publisher","first-page":"2587","DOI":"10.1109\/TIP.2020.3048632","volume":"30","author":"Y Zhong","year":"2021","unstructured":"Zhong Y, Deng W, Hu J et al (2021) Sface: sigmoid-constrained hypersphere loss for robust face recognition. IEEE Trans Image Process 30:2587\u20132598","journal-title":"IEEE Trans Image Process"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08732-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08732-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08732-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T15:20:28Z","timestamp":1692026428000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08732-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,16]]},"references-count":46,"journal-issue":{"issue":"26","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["8732"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08732-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,16]]},"assertion":[{"value":"16 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}