Optimal Transport for Domain Adaptation

rabin, 2012, Wasserstein barycenter and its application to texture mixing, Proc Scale Space Variational Methods Comput Vis, 435, 10.1007/978-3-642-24785-9_37

10.1109/MSP.2014.2347059

10.1109/ICCV.2013.274

kumar, 2012, Generalized multiview analysis: A discriminative latent space, Proc IEEE Conf Comput Vis Pattern Recognit, 2160

10.1109/CVPR.2011.5995702

10.1137/060659624

10.1109/TNN.2010.2091281

10.1109/TKDE.2009.191

mansour, 2009, Domain adaptation: Learning bounds and algorithms, Proc Conf Learn Theory, 19

10.1109/34.954602

jhuo, 2012, Robust visual domain adaptation with low-rank reconstruction, Proc IEEE Conf Comput Vis Pattern Recognit, 2168

hoffman, 2013, Efficient learning of domain invariant image representations, Proc Int Conf Learn Representations

kantorovich, 1942, On the translocation of masses, C R (Doklady) Acad Sci URSS (N S ), 37, 199

ben-david, 2010, Impossibility theorems for domain adaptation, Proc Conf Artif Intell Statist, 129

ahuja, 1993, Network Flows Theory Algorithms and Applications

10.1007/978-3-642-38267-3_36

germain, 2013, A PAC-Bayesian approach for domain adaptation with specialization to linear classifiers, Proc Int Conf Mach Learn, 738

10.1007/BF02392620

10.1109/ICCV.2011.6126344

gong, 2012, Geodesic flow kernel for unsupervised domain adaptation, Proc IEEE Conf Comput Vis Pattern Recognit, 2066

ham, 2005, Semisupervised alignment of manifolds, Proc 10th Int Workshop Artif Intell Statist, 120

griffin, 2007, Caltech-256 object category dataset

wang, 2009, Manifold alignment without correspondence, Proc Int Joint Conf Artif Intell, 1273

wang, 2011, Heterogeneous domain adaptation using manifold alignment, Proc Int Joint Conf Artif Intell, 1541

zheng, 2012, A Grassmann manifold-based domain adaptation approach, Proc Int Conf Pattern Recognit, 2095

zhang, 2013, Covariate shift in Hilbert space: A solution via surrogate kernels, Proc 30th Int Conf Mach Learn, 388

10.1109/TPAMI.2006.207

10.1109/TPAMI.2009.28

10.1109/ICCV.1998.710701

carlier, 2014, Numerical methods for matching for teams and Wasserstein barycenters

carreira-perpinan, 2014, LASS: A simple assignment model with Laplacian smoothing, Proc 28th AAAI Conf Artif Intell, 1715

courty, 2014, Domain adaptation with regularized optimal transport, Proc Eur Conf Mach Learn Principles Practice Knowl Discovery Databases, 1

cuturi, 2013, Sinkhorn distances: Lightspeed computation of optimal transportation, Proc Advances Neural Inf Process Syst, 2292

cuturi, 2014, Ground metric learning, J Mach Learn Res, 15, 533

cuturi, 2014, Fast computation of Wasserstein barycenters, Proc Int Conf Mach Learn, 685

daumé, 2007, Frustratingly easy domain adaptation, Proc 32nd Ann Meeting Assoc for Computational Linguistics

donahue, 2014, DeCAF: A deep convolutional activation feature for generic visual recognition, Proc Int Conf Mach Learn, 647

bertsekas, 1999, Nonlinear Programming

10.1007/s002110050002

10.1145/2070781.2024192

10.1007/s10851-014-0506-3

bredies, 2005, Equivalence of a Generalized Conditional Gradient Method and the Method of Surrogate Functionals

10.1007/s10589-007-9083-3

10.1201/b11431-6

10.1109/TPAMI.2009.57

10.1371/journal.pone.0148655

sugiyama, 2008, Direct importance estimation with model selection and its application to covariate shift adaptation, Proc Adv Neural Inf Process Syst

10.1007/978-3-540-71050-9

10.1109/Multi-Temp.2015.7245773

10.1007/978-3-319-20828-2

10.1007/978-3-642-15561-1_16

solomon, 2014, Wasserstein propagation for semi-supervised learning, Proc Int Conf Mach Learn, 306

10.1109/TKDE.2009.126