{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:37:14Z","timestamp":1775745434362,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Sci. Eng."],"published-print":{"date-parts":[[2020,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We propose a transfer metric learning method to infer domain-specific data embeddings for unseen domains, from which no data are given in the training phase, by using knowledge transferred from related domains. When training and test distributions are different, the standard metric learning cannot infer appropriate data embeddings. The proposed method can infer appropriate data embeddings for the unseen domains by using latent domain vectors, which are latent representations of domains and control the property of data embeddings for each domain. This latent domain vector is inferred by using a neural network that takes the set of feature vectors in the domain as an input. The neural network is trained without the unseen domains.\nThe proposed method can instantly infer data embeddings for the unseen domains without (re)-training once the sets of feature vectors in the domains are given. To accumulate knowledge in advance, the proposed method uses labeled and unlabeled data in multiple source domains. Labeled data, i.e., data with label information such as class labels or pair (similar\/dissimilar) constraints, are used for learning data embeddings in such a way that similar data points are close and dissimilar data points are separated in the embedding space. Although unlabeled data do not have labels, they have geometric information that characterizes domains. The proposed method incorporates this information in a natural way on the basis of a probabilistic framework.\nThe conditional distributions of the latent domain vectors, the embedded data, and the observed data are parameterized by neural networks and are optimized by maximizing the variational lower bound using stochastic gradient descent. The effectiveness of the proposed method was demonstrated through experiments using three clustering tasks.<\/jats:p>","DOI":"10.1007\/s41019-020-00125-1","type":"journal-article","created":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T06:02:17Z","timestamp":1590386537000},"page":"140-151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Transfer Metric Learning for Unseen Domains"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2915-4615","authenticated-orcid":false,"given":"Atsutoshi","family":"Kumagai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoharu","family":"Iwata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhiro","family":"Fujiwara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"125_CR1","unstructured":"Arthur D, Vassilvitskii S (2007) K-means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms. Society for Industrial and Applied Mathematics, pp 1027\u20131035"},{"key":"125_CR2","doi-asserted-by":"crossref","unstructured":"Babar S, Mahalle P, Stango A, Prasad N, Prasad R (2010) Proposed security model and threat taxonomy for the Internet of Things (IoT). In: ICNSA","DOI":"10.1007\/978-3-642-14478-3_42"},{"key":"125_CR3","unstructured":"Balaji Y, Sankaranarayanan S, Chellappa R (2018) Metareg: towards domain generalization using meta-regularization. In: NeurIPS"},{"key":"125_CR4","unstructured":"Bellet A, Habrard A, Sebban M (2013) A survey on metric learning for feature vectors and structured data. arXiv"},{"key":"125_CR5","doi-asserted-by":"crossref","unstructured":"Bhattarai B, Sharma G, Jurie F (2016) CP-MTML: coupled projection multi-task metric learning for large scale face retrieval. In: CVPR","DOI":"10.1109\/CVPR.2016.458"},{"key":"125_CR6","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin"},{"key":"125_CR7","doi-asserted-by":"crossref","unstructured":"Blumenstein K, Niederer C, Wagner M, Schmiedl G, Rind A, Aigner W (2016) Evaluating information visualization on mobile devices: gaps and challenges in the empirical evaluation design space. In: Proceedings of the sixth workshop on BELIV","DOI":"10.1145\/2993901.2993906"},{"key":"125_CR8","unstructured":"Cao B, Ni X, Sun J-T, Wang G, Yang Q (2011) Distance metric learning under covariate shift. In: IJCAI"},{"key":"125_CR9","doi-asserted-by":"crossref","unstructured":"Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: ICML","DOI":"10.1145\/1273496.1273523"},{"key":"125_CR10","unstructured":"Edwards H, Storkey A (2017) Towards a neural statistician. In: ICLR"},{"key":"125_CR11","doi-asserted-by":"crossref","unstructured":"Fang C, Xu Y, Rockmore DN (2013) Unbiased metric learning: on the utilization of multiple datasets and web images for softening bias. In: ICCV","DOI":"10.1109\/ICCV.2013.208"},{"issue":"59","key":"125_CR12","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(59):1\u201335","journal-title":"J Mach Learn Res"},{"issue":"10","key":"125_CR13","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1109\/TIP.2011.2134107","volume":"20","author":"B Geng","year":"2011","unstructured":"Geng B, Tao D, Xu C (2011) Daml: domain adaptation metric learning. IEEE Trans Image Process 20(10):2980\u20132989","journal-title":"IEEE Trans Image Process"},{"key":"125_CR14","doi-asserted-by":"crossref","unstructured":"Ghifary M, Bastiaan\u00a0Kleijn W, Zhang M, Balduzzi D (2015) Domain generalization for object recognition with multi-task autoencoders. In: ICCV","DOI":"10.1109\/ICCV.2015.293"},{"key":"125_CR15","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: a deep learning approach. In: ICML"},{"key":"125_CR16","unstructured":"Goldberger J, Hinton GE, Roweis ST, Salakhutdinov RR (2005) Neighbourhood components analysis. In: NeurIPS"},{"key":"125_CR17","unstructured":"Gong B, Grauman K, Sha F (2013) Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: ICML"},{"key":"125_CR18","unstructured":"Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: CVPR"},{"issue":"Mar","key":"125_CR19","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton A, Borgwardt KM, Rasch MJ, Sch\u00f6lkopf B, Smola A (2012) A kernel two-sample test. JMLR 13(Mar):723\u2013773","journal-title":"JMLR"},{"issue":"8","key":"125_CR20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"125_CR21","doi-asserted-by":"crossref","unstructured":"Hu J, Lu J, Tan Y-P (2015) Deep transfer metric learning. In: CVPR","DOI":"10.1109\/CVPR.2015.7298629"},{"key":"125_CR22","doi-asserted-by":"crossref","unstructured":"Jung S-U, Chung Y-S, Yoo J-H, Moon K-Y (2008) Real-time face verification for mobile platforms. In: VC","DOI":"10.1007\/978-3-540-89646-3_81"},{"issue":"2\u20133","key":"125_CR23","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1023\/B:VLSI.0000027483.39774.f8","volume":"37","author":"S Kaski","year":"2004","unstructured":"Kaski S, Sinkkonen J (2004) Principle of learning metrics for exploratory data analysis. J VLSI Signal Process Syst Signal Image Video Technol 37(2\u20133):177\u2013188","journal-title":"J VLSI Signal Process Syst Signal Image Video Technol"},{"key":"125_CR24","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv"},{"key":"125_CR25","unstructured":"Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: ICLR"},{"key":"125_CR26","unstructured":"Kumagai A, Iwata T (2018) Zero-shot domain adaptation without domain semantic descriptors. arXiv"},{"key":"125_CR27","doi-asserted-by":"crossref","unstructured":"Li D, Yang Y, Song Y-Z, Hospedales TM (2017) Deeper, broader and artier domain generalization. In: ICCV","DOI":"10.1109\/ICCV.2017.591"},{"issue":"9","key":"125_CR28","doi-asserted-by":"publisher","first-page":"3789","DOI":"10.1109\/TIP.2014.2332398","volume":"23","author":"Y Luo","year":"2014","unstructured":"Luo Y, Liu T, Tao D, Xu C (2014) Decomposition-based transfer distance metric learning for image classification. IEEE Trans Image Process 23(9):3789\u20133801","journal-title":"IEEE Trans Image Process"},{"key":"125_CR29","unstructured":"Luo Y, Wen Y, Duan L, Tao D (2018) Transfer metric learning: algorithms, applications and outlooks. arXiv"},{"issue":"Nov","key":"125_CR30","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579\u20132605","journal-title":"J Mach Learn Res"},{"issue":"3","key":"125_CR31","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1109\/TCSVT.2016.2619498","volume":"27","author":"N McLaughlin","year":"2017","unstructured":"McLaughlin N, del Rincon JM, Miller PC (2017) Person reidentification using deep convnets with multitask learning. IEEE Trans Circuits Syst Video Technol 27(3):525\u2013539","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"125_CR32","doi-asserted-by":"crossref","unstructured":"Motiian S, Piccirilli M, Adjeroh DA, Doretto G (2017) Unified deep supervised domain adaptation and generalization. In: ICCV","DOI":"10.1109\/ICCV.2017.609"},{"key":"125_CR33","unstructured":"Muandet K, Balduzzi D, Sch\u00f6lkopf B (2013) Domain generalization via invariant feature representation. In: ICML"},{"key":"125_CR34","unstructured":"Parameswaran S, Weinberger KQ (2010) Large margin multi-task metric learning. In: NeurIPS"},{"key":"125_CR35","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: NeurIPS"},{"key":"125_CR36","unstructured":"Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. In: NeurIPS"},{"key":"125_CR37","doi-asserted-by":"crossref","unstructured":"Sohn K, Liu S, Zhong G, Yu X, Yang M-H, Chandraker M (2017) Unsupervised domain adaptation for face recognition in unlabeled videos. In: CVPR","DOI":"10.1109\/ICCV.2017.630"},{"key":"125_CR38","unstructured":"Sohn K, Shang W, Yu X, Chandraker M (2019) Unsupervised domain adaptation for distance metric learning. In: ICLR"},{"key":"125_CR39","doi-asserted-by":"crossref","unstructured":"Song J, Yang Y, Song Y-Z, Xiang T, Hospedales TM (2019) Generalizable person re-identification by domain-invariant mapping network. CVPR","DOI":"10.1109\/CVPR.2019.00081"},{"key":"125_CR40","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In: CVPR","DOI":"10.1109\/CVPR.2018.00131"},{"key":"125_CR41","doi-asserted-by":"crossref","unstructured":"Vanschoren J (2018) Meta-learning: a survey. arXiv","DOI":"10.1007\/978-3-030-05318-5_2"},{"key":"125_CR42","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D et\u00a0al (2016) Matching networks for one shot learning. In: NeurIPS"},{"key":"125_CR43","doi-asserted-by":"crossref","unstructured":"Wang J, Song Y, Leung T, Rosenberg C, Wang J, Philbin J, Chen B, Wu Y (2014) Learning fine-grained image similarity with deep ranking. In: CVPR","DOI":"10.1109\/CVPR.2014.180"},{"key":"125_CR44","unstructured":"Weinberger KQ, Blitzer J, Saul LK (2006) Distance metric learning for large margin nearest neighbor classification. In: NeurIPS"},{"key":"125_CR45","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.patcog.2017.06.032","volume":"72","author":"X Xiao","year":"2017","unstructured":"Xiao X, Jin L, Yang Y, Yang W, Sun J, Chang T (2017) Building fast and compact convolutional neural networks for offline handwritten chinese character recognition. Pattern Recognit 72:72\u201381","journal-title":"Pattern Recognit"},{"key":"125_CR46","unstructured":"Xing EP, Jordan MI, Russell SJ, Ng AY (2003) Distance metric learning with application to clustering with side-information. In: NeurIPS"},{"issue":"1","key":"125_CR47","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s41044-018-0029-9","volume":"3","author":"P Yang","year":"2018","unstructured":"Yang P, Huang K, Hussain A (2018) A review on multi-task metric learning. Big Data Anal 3(1):3","journal-title":"Big Data Anal"},{"issue":"4","key":"125_CR48","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.1016\/j.patcog.2009.11.005","volume":"43","author":"X Yin","year":"2010","unstructured":"Yin X, Chen S, Hu E, Zhang D (2010) Semi-supervised clustering with metric learning: an adaptive kernel method. Pattern Recognit 43(4):1320\u20131333","journal-title":"Pattern Recognit"},{"key":"125_CR49","unstructured":"Zaheer M, Kottur S, Ravanbakhsh S, Poczos B, Salakhutdinov RR, Smola AJ (2017) Deep sets. In: NeurIPS"}],"container-title":["Data Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-020-00125-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41019-020-00125-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-020-00125-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T23:47:13Z","timestamp":1621900033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41019-020-00125-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["125"],"URL":"https:\/\/doi.org\/10.1007\/s41019-020-00125-1","relation":{},"ISSN":["2364-1185","2364-1541"],"issn-type":[{"value":"2364-1185","type":"print"},{"value":"2364-1541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,25]]},"assertion":[{"value":"9 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}