2015

Optimal Transport for Domain Adaptation

Courty, Nicolas, Flamary, Rémi, Tuia, Devis et al.

Understand

Domain adaptation from one data space (or domain) to another is one of the most challenging tasks of modern data analytics.

If the adaptation is done correctly, models built on a specific data space become more robust when confronted to data depicting the same semantic concepts (the classes), but observed by another observation system with its own specificities.
Among the many strategies proposed to adapt a domain to another, finding a common representation has shown excellent properties: by finding a common representation for both domains, a single classifier can be effective in both and use labelled samples from the source domain to predict the unlabelled samples of the target domain.
In this paper, we propose a regularized unsupervised optimal transportation model to perform the alignment of the representations in the source and target domains.

Built on

L. Kantorovich, “On the translocation of masses,”
1942
Earlier work this paper cites.
R. K. Ahuja, T. L. Magnanti, and J. B. Orlin,
1993
Earlier work this paper cites.
W. Gangbo and R. J. McCann, “The geometry of optimal transportation,”
1996
Earlier work this paper cites.
Y. Rubner, C. Tomasi, and L. Guibas, “A metric for distributions with applications to image databases,” in
1998
Earlier work this paper cites.
D. P. Bertsekas,
1999
Earlier work this paper cites.
J.-D. Benamou and Y. Brenier, “A computational fluid mechanics solution to the monge-kantorovich mass transfer problem,”
2000
Earlier work this paper cites.
B. Luo and R. Hancock, “Structural graph matching using the em algorithm and singular value decomposition,”
2001
Earlier work this paper cites.
K. Bredies, D. Lorenz, and P. Maass,
2005
Earlier work this paper cites.
J. Ham, D. Lee, and L. Saul, “Semisupervised alignment of manifolds,” in
2005
Earlier work this paper cites.
T. S. Caetano, T. Caelli, D. Schuurmans, and D. Barone, “Grapihcal models and point pattern matching,”
2006
Earlier work this paper cites.
H. Daumé III, “Frustratingly easy domain adaptation,” in
2007
Earlier work this paper cites.
G. Griffin, A. Holub, and P. Perona, “Caltech-256 Object Category Dataset,” California Institute of Technology, Tech. Rep. CNS-TR-2007-001, 2007
2007
Earlier work this paper cites.
P. Knight, “The sinkhorn-knopp algorithm: Convergence and applications,”
2008
Earlier work this paper cites.
M. Sugiyama, S. Nakajima, H. Kashima, P. Buenau, and M. Kawanabe, “Direct importance estimation with model selection and its application to covariate shift adaptation,” in
2008
Earlier work this paper cites.
K. Bredies, D. A. Lorenz, and P. Maass, “A generalized conditional gradient method and its connection to an iterative shrinkage method,”
2009
Earlier work this paper cites.
T. S. Caetano, J. J. McAuley, L. Cheng, Q. V. Le, and A. J. Smola, “Learning graph matching,”
2009
Earlier work this paper cites.
Y. Mansour, M. Mohri, and A. Rostamizadeh, “Domain adaptation: Learning bounds and algorithms,” in
2009
Earlier work this paper cites.
C. Villani,
2009
Earlier work this paper cites.

Similar

C. Wang and S. Mahadevan, “Manifold alignment without correspondence,” in
2009
Cited alongside, same era.
S. Ben-David, T. Luu, T. Lu, and D. Pál, “Impossibility theorems for domain adaptation.” in
2010
Cited alongside, same era.
L. Bruzzone and M. Marconcini, “Domain adaptation problems: A dasvm classification technique and a circular validation strategy,”
2010
Cited alongside, same era.
S. J. Pan and Q. Yang, “A survey on transfer learning,”
2010
Cited alongside, same era.
K. Saenko, B. Kulis, M. Fritz, and T. Darrell, “Adapting visual category models to new domains,” in
2010
Cited alongside, same era.
S. Si, D. Tao, and B. Geng, “Bregman divergence-based regularization for transfer subspace learning,”
2010
Cited alongside, same era.
N. Bonneel, M. van de Panne, S. Paris, and W. Heidrich, “Displacement interpolation using Lagrangian mass transport,”
2011
Cited alongside, same era.
R. Gopalan, R. Li, and R. Chellappa, “Domain adaptation for object recognition: An unsupervised approach,” in
2011
Cited alongside, same era.
B. Kulis, K. Saenko, and T. Darrell, “What you saw is not what you get: domain adaptation using asymmetric kernel transforms,” in
2011
Cited alongside, same era.
——, “Domain adaptation via transfer component analysis,”
2011
Cited alongside, same era.
C. Wang, P. Krafft, and S. Mahadevan, “Manifold alignment,” in
2011
Cited alongside, same era.
——, “Heterogeneous domain adaptation using manifold alignment,” in
2011
Cited alongside, same era.

Then

J. Hoffman, E. Rodner, J. Donahue, K. Saenko, and T. Darrell, “Efficient learning of domain invariant image representations,” in
2013
Later among the works it cites.
——, “Efficient learning of domain-invariant image representations,” in
2013
Later among the works it cites.
M. Long, J. Wang, G. Ding, J. Sun, and P. Yu, “Transfer feature learning with joint distribution adaptation,” in
2013
Later among the works it cites.
K. Zhang, V. W. Zheng, Q. Wang, J. T. Kwok, Q. Yang, and I. Marsic, “Covariate shift in Hilbert space: A solution via surrogate kernels,” in
2013
Later among the works it cites.
J. Zheng, M.-Y. Liu, R. Chellappa, and P. Phillips, “A Grassmann manifold-based domain adaptation approach,” in
2013
Later among the works it cites.
G. Carlier, A. Oberman, and E. Oudet, “Numerical methods for matching for teams and Wasserstein barycenters,” Inria, Tech. Rep. hal-00987292, 2014
2014
Later among the works it cites.
M. Carreira-Perpinan and W. Wang, “LASS: A simple assignment model with laplacian smoothing,” in
2014
Later among the works it cites.
N. Courty, R. Flamary, and D. Tuia, “Domain adaptation with regularized optimal transport,” in
2014
Later among the works it cites.
M. Cuturi and D. Avis, “Ground metric learning,”
2014
Later among the works it cites.
M. Cuturi and A. Doucet, “Fast computation of Wasserstein barycenters,” in
2014
Later among the works it cites.
J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell, “DeCAF: a deep convolutional activation feature for generic visual recognition,” in
2014
Later among the works it cites.
J. Solomon, R. Rustamov, G. Leonidas, and A. Butscher, “Wasserstein propagation for semi-supervised learning,” in
2014
Later among the works it cites.
N. Bonneel, J. Rabin, G. Peyré, and H. Pfister, “Sliced and radon Wasserstein barycenters of measures,”
2015
Closest in time.
V. M. Patel, R. Gopalan, R. Li, and R. Chellappa, “Visual domain adaptation: an overview of recent advances,”
2015
Closest in time.
F. Santambrogio, “Optimal transport for applied mathematicians,”
2015
Closest in time.
D. Tuia, R. Flamary, A. Rakotomamonjy, and N. Courty, “Multitemporal classification without new labels: a solution with optimal transport,” in
2015
Closest in time.
D. Tuia and G. Camps-Valls, “Kernel manifold alignment for domain adaptation,”
2016
Closest in time.
B. Gong, Y. Shi, F. Sha, and K. Grauman, “Geodesic flow kernel for unsupervised domain adaptation.” in
2073
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…