Unsupervised adaptation across domain shifts by generating intermediate data representations

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 36, Issue 11, 2014, Pages 2288-2302

  Gopalan, Raghuraman ^a   Li, Ruonan ^b   Chellappa, Rama ^c  

^a AT AND T LABS RESEARCH   (United States)

^b HARVARD UNIVERSITY   (United States)

^c UNIVERSITY OF MARYLAND   (United States)

Author keywords

Domain adaptation; Grassmann manifold; Object recognition; Unsupervised

Indexed keywords

DATA REPRESENTATIONS; DOMAIN ADAPTATION; GRASSMANN MANIFOLD; UNSUPERVISED; UNSUPERVISED ADAPTATION;

OBJECT RECOGNITION;

EID: 84901386413     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2013.249     Document Type: Article

References (58)

1. P.-A. Absil, R. Mahony, and R. Sepulchre, "Riemannian geometry of Grassmann manifolds with a view on algorithmic computation," Acta Appl. Math., vol. 80, pp. 199-220, Feb. 2004.
2. H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "Speeded-up robust features (SURF)," Comput. Vis. Image Understanding, vol. 110, pp. 346-359, Jun. 2008.
3. P. Belhumeur, J. Hespanha, and D. Kriegman, "Eigenfaces vs. fisherfaces: Recognition using class specific linear projection," IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 711-720, Jul. 1997.
4. M. Belkin and P. Niyogi, "Laplacian eigenmaps for dimensionality reduction and data representation," Neural Comput., vol. 15, pp. 1373-1376, Jun. 2003.
5. S. Ben-David, J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. W. Vaughan, "A theory of learning from different domains," Mach. Learn., vol. 79, pp. 151-175, May 2010.
6. S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira, "Analysis of representations for domain adaptation," in Proc. Advances Neural Inf. Process. Syst., Dec. 2007, pp. 137-145.
7. S. Ben-David, T. Luu, T. Lu, and D. Pal, "Impossibility theorems for domain adaptation," in Proc. 13th Int. Conf. Artif. Intell. Statist., Sardinia, Italy, May 2010, pp. 129-136.
8. D. Benbouzid, R. Busa-Fekete, N. Casagrande, F.-D. Collin, and B. Kégl, "Multiboost: A multi-purpose boosting package," J. Mach. Learn. Res., vol. 13, pp. 549-553, Mar. 2012.
9. A. Bergamo and L. Torresani, "Exploiting weakly-labeled web images to improve object classification: A domain adaptation approach," in Proc. Advances Neural Inf. Process. Syst., Vancouver, Canada, Dec. 2010, pp. 181-189.
10. J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. Wortman, "Learning bounds for domain adaptation," in Proc. Advances Neural Inf. Process. Syst., Vancouver, BC, Canada, Dec. 2008, pp. 129- 136.
11. J. Blitzer, M. Dredze, and F. Pereira, "Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification," in 45th Annu. Meeting Assoc. Comput. Linguistics, Prague, Czech Republic, Jun. 2007, pp. 440-447.
12. J. Blitzer, D. Foster, and S. Kakade, "Domain adaptation with coupled subspaces," in Proc. Artif. Intell. Statist., Apr. 2011, pp. 173- 181.
13. J. Blitzer, R. McDonald, and F. Pereira, "Domain adaptation with structural correspondence learning," in Proc. Conf. Empirical Methods Natural Language Process., Sydney, N.S.W., Australia, Jul. 2006, pp. 120-128.
14. L. Bruzzone and M. Marconcini, "Domain adaptation problems: A DASVM classification technique and a circular validation strategy," IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 5, pp. 770- 787, May 2010.
15. M. Chen, K. Weinberger, and J. Blitzer, "Co-Training for Domain Adaptation," in Proc. Advances Neural Inf. Process. Syst., Dec. 2011, pp. 2456-2464.
16. Y. Chikuse, Statistics on Special Manifolds, volume 174 of Lecture Notes in Statistics. New York, NY, USA: Springer Verlag, 2003.
17. W. Dai, G. Xue, Q. Yang, and Y. Yu, "Transferring naive Bayes classifiers for text classification," in Proc. Nat. Conf. Artif. Intell., Vancouver, BC, Canada, Jul. 2007, pp. 540-543.
18. H. Daumé III, A. Kumar, and A. Saha, "Co-regularization based semi-supervised domain adaptation," in Proc. Advances Neural Inf. Process. Syst., Vancouver, BC, Canada, Dec. 2010, pp. 478-486.
19. H. Daumé III and D. Marcu, "Domain adaptation for statistical classifiers," J. Artif. Intell. Res., vol. 26, pp. 101-126, May 2006.
20. M. Dredze and K. Crammer, "Online methods for multi-domain learning and adaptation," in Proc. Conf. Empirical Methods Natural Language Process., Honolulu, HI, USA, Oct. 2008, pp. 689-697.
21. L. Duan, I. Tsang, D. Xu, and T. Chua, "Domain adaptation from multiple sources via auxiliary classifiers," in Proc. 26th Annu. Int. Conf. Mach. Learn.,Montreal, QC, Canada, Jun. 2009, pp. 289-296.
22. L. Duan, I. W. Tsang, and D. Xu, "Domain transfer multiple kernel learning," IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 3, pp. 465-479, Mar. 2012.
23. L. Duan, D. Xu, and S.-F. Chang, "Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Jun. 2012, pp. 1338-1345.
24. A. Edelman, T. Arias, and S. Smith, "The geometry of algorithms with orthogonality constraints," SIAM J. Matrix Anal. Appl., vol. 20, pp. 303-353, Apr. 1999.
25. K. Etemad and R. Chellappa, "Discriminant analysis for recognition of human face images," J. Opt. Soc. Amer., vol. 14, pp. 1724- 1733, Aug. 1997.
26. K. Gallivan, A. Srivastava, X. Liu, and P. Van Dooren, "Efficient algorithms for inferences on grassmann manifolds," in Proc. IEEE Workshop Statist. Signal Process., St. Louis, MO, USA, Sep. 2003, pp. 315-318.
27. X. Glorot, A. Bordes, and Y. Bengio, "Domain adaptation for large-scale sentiment classification: A deep learning approach," in Proc. 28th Int. Conf. Mach. Learn., Apr. 2011, pp. 513-520.
28. B. Gong, Y. Shi, F. Sha, and K. Grauman, "Geodesic flow kernel for unsupervised domain adaptation," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Jun. 2012, pp. 2066-2073.
29. R. Gopalan, R. Li, and R. Chellappa, "Domain adaptation for object recognition: An unsupervised approach," Proc. IEEE Int. Conf. Comput. Vis., Nov. 2011, pp. 999-1006.
30. J. Hamm and D. D. Lee, "Grassmann discriminant analysis: A unifying view on subspace-based learning," in Proc. 25th Int. Conf. Mach. Learn., Helsinki, Finland, Jul. 2008, pp. 376-383.
31. M. Harandi, S. Shirazi, C. Sanderson, and B. Lovell, "Graph embedding discriminant analysis on grassmannian manifolds for improved image set matching," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Colorado Springs, CO, USA, Jun. 2011, pp. 2705- 2512.
32. J. Hoffman, B. Kulis, T. Darrell, and K. Saenko, "Discovering latent domains for multisource domain adaptation," in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 702-715.
33. N. Japkowicz and S. Stephen, "The class imbalance problem: A systematic study," Intell. Data Anal., vol. 6, pp. 429-449, Oct. 2002.
34. I.-H. Jhuo, D. Liu, D. T. Lee, and S.-F. Chang, "Robust visual domain adaptation with low-rank reconstruction," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Jun. 2012, pp. 2168-2175.
35. J. Jiang, "A literature survey on domain adaptation of statistical classifiers," 2008.
36. H. Karcher, "Riemannian center of mass and mollifier smoothing," Commun. Pure Appl. Math., vol. 30, pp. 509-541, May 1977.
37. B. Kulis, K. Saenko, and T. Darrell, "What you saw is not what you get: Domain adaptation using asymmetric kernel transforms," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Jun. 2011, pp. 1785-1792.
38. K. Lai and D. Fox, "Object recognition in 3D point clouds using web data and domain adaptation," Int. J. Robotics Res., vol. 29, pp. 1019-1028, Aug. 2010.
39. Y. M. Lui and J. R. Beveridge, "Grassmann registration manifolds for face recognition," in Proc. 10th Eur. Conf. Comput. Vis., Marseille, France, Oct. 2008, pp. 44-57.
40. Y. Mansour, M. Mohri, and A. Rostamizadeh, "Domain adaptation: Learning bounds and algorithms," Arxiv preprint arXiv:0902.3430, 2009.
41. Y. Mansour, M. Mohri, and A. Rostamizadeh, "Domain adaptation with multiple sources," in Proc. Advances Neural Inf. Process. Syst., Vancouver, BC, Canada, Dec. 2009, pp. 1041-1048.
42. S. Mika, G. Ratsch, J. Weston, B. Scholkopf, and K. Mullers, "Fisher discriminant analysis with kernels," in Proc. IEEE Signal Process. Soc. Workshop Neural Netw. Signal Process. IX, Aug. 1999, pp. 41-48.
43. S. J. Pan, I. Tsang, J. Kwok, and Q. Yang, "Domain adaptation via transfer component analysis," IEEE Trans. Neural Netw., vol. 22, no. 2, pp. 199-210, Feb. 2011.
44. S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345-1359, Oct. 2010.
45. K. Saenko, B. Kulis, M. Fritz, and T. Darrell, "Adapting visual category models to new domains," in Proc. 11th Eur. Conf. Comput. Vis., Heraklion, Greece, Sep. 2010, pp. 213-226.
46. R. E. Schapire and Y. Singer, "Improved boosting algorithms using confidence-rated predictions," Mach. Learn., vol. 37, pp. 297-336, Dec. 1999.
47. Y. Shi and F. Sha, "Information-theoretical learning of discriminative clusters for unsupervised domain adaptation," in Proc. 29th Int. Conf. Mach. Learn., Jun. 2012, pp. 1079-1086.
48. H. Shimodaira, "Improving predictive inference under covariate shift by weighting the log-likelihood function," J. Statist. Planning Inference, vol. 90, pp. 227-244, Oct. 2000.
49. G. Tur, "Co-adaptation: Adaptive co-training for semi-supervised learning," in Proc. Int. Conf. Acoustics, Speech, Signal Process., Taipei, Taiwan, Apr. 2009, pp. 3721-3724.
50. P. Turaga, A. Veeraraghavan, and R. Chellappa, "Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Anchorage, AK, USA, Jun. 2008, pp. 1-8.
51. M. Turk and A. Pentland, "Face recognition using eigenfaces," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., Maui, HI, USA, Jun. 1991, pp. 586-591.
52. C. Wang and S. Mahadevan, "Manifold alignment without correspondence," in Proc. 21st Int. Joint Conf. Artif. Intell., Pasadena, CA, USA, Jul. 2009, pp. 1273-1278.
53. H. Wold, "Partial least squares," in Encyclopedia of Statistical Sciences, vol. 6, New York, NY, USA: Wiley, 1985.
54. Y. Wong, "Differential geometry of Grassmann manifolds," Proc. Nat. Acad. Sci., vol. 57, pp. 589-594, Mar. 1967.
55. D. Xing, W. Dai, G. Xue, and Y. Yu, "Bridged refinement for transfer learning," in Proc. 11th Eur. Conf. Principles Practice Knowl. Discovery Databases, Sep. 2007, pp. 324-335.
56. S. Yan, D. Xu, B. Zhang, H.-J. Zhang, Q. Yang, and S. Lin, "Graph embedding and extensions: A general framework for dimensionality reduction," IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 1, pp. 40-51, Jan. 2007.
57. J. Yang, R. Yan, and A. G. Hauptmann, "Cross-domain video concept detection using adaptive svms," in Proc. 15th Int. Conf. Multimedia, 2007, pp. 188-197.
58. J. Zheng, M.-Y. Liu, R. Chellappa, and P. Phillips, "A grassmann manifold-based domain adaptation approach," in Proc. Int. Conf. Pattern Recog., Nov. 2012, pp. 2095-2099.