Advertisement

Transfer Neural Trees for Heterogeneous Domain Adaptation

  • Wei-Yu Chen
  • Tzu-Ming Harry Hsu
  • Yao-Hung Hubert Tsai
  • Yu-Chiang Frank WangEmail author
  • Ming-Syan Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9909)

Abstract

Heterogeneous domain adaptation (HDA) addresses the task of associating data not only across dissimilar domains but also described by different types of features. Inspired by the recent advances of neural networks and deep learning, we propose Transfer Neural Trees (TNT) which jointly solves cross-domain feature mapping, adaptation, and classification in a NN-based architecture. As the prediction layer in TNT, we further propose Transfer Neural Decision Forest (Transfer-NDF), which effectively adapts the neurons in TNT for adaptation by stochastic pruning. Moreover, to address semi-supervised HDA, a unique embedding loss term for preserving prediction and structural consistency between target-domain data is introduced into TNT. Experiments on classification tasks across features, datasets, and modalities successfully verify the effectiveness of our TNT.

Keywords

Transfer learning Domain adaptation Neural Decision Forest Neural network 

Supplementary material

419978_1_En_25_MOESM1_ESM.pdf (196 kb)
Supplementary material 1 (pdf 195 KB)

References

  1. 1.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  2. 2.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Zhu, Y., Chen, Y., Lu, Z., Pan, S.J., Xue, G.R., Yu, Y., Yang, Q.: Heterogeneous transfer learning for image classification. In: AAAI (2011)Google Scholar
  4. 4.
    Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: IEEE ICCV (2015)Google Scholar
  5. 5.
    Chidlovskii, B., Csurka, G., Gangwar, S.: Assembling heterogeneous domain adaptation methods for image classification. In: CLEF (Working Notes) (2014)Google Scholar
  6. 6.
    Dai, W., Chen, Y., Xue, G.R., Yang, Q., Yu, Y.: Translated learning: transfer learning across different feature spaces. In: NIPS (2008)Google Scholar
  7. 7.
    Prettenhofer, P., Stein, B.: Cross-language text classification using structural correspondence learning. In: ACL (2010)Google Scholar
  8. 8.
    Daumé III, H.: Frustratingly easy domain adaptation. In: ACL (2007)Google Scholar
  9. 9.
    Daumé III, H., Kumar, A., Saha, A.: Frustratingly easy semi-supervised domain adaptation. In: Natural Language Processing Workshop (2010)Google Scholar
  10. 10.
    Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Networks 22(2), 199–210 (2011)CrossRefGoogle Scholar
  11. 11.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: IEEE CVPR (2012)Google Scholar
  12. 12.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: IEEE ICCV (2013)Google Scholar
  13. 13.
    Donahue, J., Hoffman, J., Rodner, E., Saenko, K., Darrell, T.: Semi-supervised domain adaptation with instance constraints. In: IEEE CVPR (2013)Google Scholar
  14. 14.
    Shi, X., Liu, Q., Fan, W., Yu, P.S., Zhu, R.: Transfer learning on heterogenous feature spaces via spectral transformation. In: IEEE ICDM (2010)Google Scholar
  15. 15.
    Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: IEEE CVPR (2011)Google Scholar
  16. 16.
    Wang, C., Mahadevan, S.: Heterogeneous domain adaptation using manifold alignment. In: IJCAI (2011)Google Scholar
  17. 17.
    Duan, L., Xu, D., Tsang, I.: Learning with augmented features for heterogeneous domain adaptation. In: ICML (2012)Google Scholar
  18. 18.
    Hoffman, J., Rodner, E., Donahue, J., Darrell, T., Saenko, K.: Efficient learning of domain-invariant image representations. In: ICLR (2013)Google Scholar
  19. 19.
    Zhou, J.T., Tsang, I.W., Pan, S.J., Tan, M.: Heterogeneous domain adaptation for multiple classes. In: AISTATS (2014)Google Scholar
  20. 20.
    Wu, X., Wang, H., Liu, C., Jia, Y.: Cross-view action recognition over heterogeneous feature spaces. In: IEEE ICCV (2013)Google Scholar
  21. 21.
    Li, W., Duan, L., Xu, D., Tsang, I.W.: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE T-PAMI 36(6), 1134–1148 (2014)CrossRefGoogle Scholar
  22. 22.
    Xiao, M., Guo, Y.: Feature space independent semi-supervised domain adaptation via kernel matching. IEEE T-PAMI 37(1), 54–66 (2015)CrossRefGoogle Scholar
  23. 23.
    Xiao, M., Guo, Y.: Semi-supervised subspace co-projection for multi-class heterogeneous domain adaptation. In: Appice, A., Rodrigues, P.P., Santos Costa, V., Gama, J., Jorge, A., Soares, C. (eds.) ECML PKDD 2015. LNCS, vol. 9285, pp. 525–540. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  24. 24.
    Yao, T., Pan, Y., Ngo, C.W., Li, H., Mei, T.: Semi-supervised domain adaptation with subspace learning for visual recognition. In: IEEE CVPR (2015)Google Scholar
  25. 25.
    Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. In: CoRR, abs/1412.3474 (2014)Google Scholar
  26. 26.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)Google Scholar
  27. 27.
    Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M.: Domain-adversarial neural networks. JMLR 17(59), 1–35 (2014)MathSciNetzbMATHGoogle Scholar
  28. 28.
    Shu, X., Qi, G.J., Tang, J., Wang, J.: Weakly-shared deep transfer networks for heterogeneous-domain knowledge propagation. In: ACM Conference on Multimedia Conference (2015)Google Scholar
  29. 29.
    Long, M., Wang, J.: Learning transferable features with deep adaptation networks. In: ICML (2015)Google Scholar
  30. 30.
    Sethi, I.K.: Entropy nets: from decision trees to neural networks. Proc. IEEE (Special Issue on Neural Networks) (1990)Google Scholar
  31. 31.
    Rota Bulo, S., Kontschieder, P.: Neural decision forests for semantic image labelling. In: IEEE CVPR (2014)Google Scholar
  32. 32.
    Kontschieder, P., Fiterau, M., Criminisi, A., Rota Bulo, S.: Deep neural decision forests. In: IEEE ICCV (2015)Google Scholar
  33. 33.
    Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007)Google Scholar
  34. 34.
    Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)Google Scholar
  35. 35.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  36. 36.
    Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from national university of singapore. In: ACM International Conference on Image and Video Retrieval (2009)Google Scholar
  37. 37.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE CVPR (2009)Google Scholar
  38. 38.
    Tommasi, T., Tuytelaars, T.: A testbed for cross-dataset analysis. In: ECCV Workshops (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Wei-Yu Chen
    • 1
    • 2
  • Tzu-Ming Harry Hsu
    • 2
  • Yao-Hung Hubert Tsai
    • 3
  • Yu-Chiang Frank Wang
    • 2
    Email author
  • Ming-Syan Chen
    • 1
  1. 1.Graduate Institute of Electrical EngineeringNational Taiwan UniversityTaipeiTaiwan
  2. 2.Research Center for Information Technology InnovationAcademia SinicaTaipeiTaiwan
  3. 3.Department of Machine LearningCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations