{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/kernel-manifold-alignment","title":"Kernel Manifold Alignment","arxiv_id":"1504.02338","date":"2015-04-09","proceeding":null,"authors":["Devis Tuia","Gustau Camps-Valls"],"abstract":"We introduce a kernel method for manifold alignment (KEMA) and domain\nadaptation that can match an arbitrary number of data sources without needing\ncorresponding pairs, just few labeled examples in all domains. KEMA has\ninteresting properties: 1) it generalizes other manifold alignment methods, 2)\nit can align manifolds of very different complexities, performing a sort of\nmanifold unfolding plus alignment, 3) it can define a domain-specific metric to\ncope with multimodal specificities, 4) it can align data spaces of different\ndimensionality, 5) it is robust to strong nonlinear feature deformations, and\n6) it is closed-form invertible which allows transfer across-domains and data\nsynthesis. We also present a reduced-rank version for computational efficiency\nand discuss the generalization performance of KEMA under Rademacher principles\nof stability. KEMA exhibits very good performance over competing methods in\nsynthetic examples, visual object recognition and recognition of facial\nexpressions tasks.","url_abs":"http://arxiv.org/abs/1504.02338v3","url_pdf":"http://arxiv.org/pdf/1504.02338v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"kernel-manifold-alignment","repo_url":"https://github.com/dtuia/KEMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}