Skip to main content
main-content
Top

Hint

Swipe to navigate through the chapters of this book

2020 | OriginalPaper | Chapter

12. Multi-Source Domain Adaptation by Deep CockTail Networks

share
SHARE

Abstract

Regular domain adaptation (DA) problems are interested in source examples drawn from a single source distribution, yet they probably come from multiple source domains in reality. Compared with DAs, Multi-Source DA (MSDA) is more challenging to settle: The extra domain shifts exist between source domains and moreover, the multi-source domains may also disagree on their semantic information. In this section, we surveyed Deep CockTail Network (DCTN), a prevalent MSDA algorithm that battles the multi-source-derived domain and semantic shifts. The ideology behind is inspired by making cocktails with multiple kinds of stuff (i.e. sources in our background). In particular, DCTN replays two alternating learning phases: (1) DCTN goes through a multi-way adversarial DA process to minimize the domain discrepancy between the target and each source, in order to obtain domain-invariant features. In this process, each target example would lead to the source-specific perplexity scores, denoting how similar each target feature appears to a feature from one of the source domains. (2) Integrated with the perplexity scores, the multi-source category classifiers categorizes target samples, and the pseudo-labeled target samples and source samples jointly update the category classifiers and the feature extractor. In the empirical studies, DCTNs are evaluated in three domain adaptation benchmarks in vanilla and source-category-shift MSDA scenarios. The results thoroughly evidence the superiority of DCTN framework that resists negative transfers across domains and tasks.

To get access to this content you need the following product:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 69.000 Bücher
  • über 500 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Testen Sie jetzt 15 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 50.000 Bücher
  • über 380 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




Testen Sie jetzt 15 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 58.000 Bücher
  • über 300 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Testen Sie jetzt 15 Tage kostenlos.

Footnotes
1
Here perplexity scores are disconnected with the term used in natural language processing. In our chapter, they are completely determined by some relevant equations.
 
2
The pre-training process can be found in the original paper and the official code in.
 
3
Since each sample x corresponds to an unique class y, \(\{\mathcal {P}_{j}\}^M_{j=1}\) and \(\mathcal {P}_t\) can be viewed as an equivalent embedding from \(\{P_{j}(x,y)\}^N_{j=1}\) and P t(x, y) that we have discussed.
 
Literature
1.
go back to reference Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1), 151–175 (2010) MathSciNetCrossRef Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1), 151–175 (2010) MathSciNetCrossRef
2.
go back to reference Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks (2016). Preprint. arXiv:1612.05424 Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks (2016). Preprint. arXiv:1612.05424
3.
go back to reference Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 248–255. IEEE, Piscataway (2009) Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 248–255. IEEE, Piscataway (2009)
4.
go back to reference Duan, L., Xu, D., Tsang, I.W.H.: Domain adaptation from multiple sources: a domain-dependent regularization approach. IEEE Trans. Neural Netw. Learn. Syst. 23(3), 504–518 (2012) CrossRef Duan, L., Xu, D., Tsang, I.W.H.: Domain adaptation from multiple sources: a domain-dependent regularization approach. IEEE Trans. Neural Netw. Learn. Syst. 23(3), 504–518 (2012) CrossRef
5.
go back to reference Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180–1189 (2015) Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180–1189 (2015)
6.
go back to reference Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2030 (2016) MathSciNetMATH Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2030 (2016) MathSciNetMATH
7.
go back to reference Gebru, T., Hoffman, J., Fei-Fei, L.: Fine-grained recognition in the wild: a multi-task domain adaptation approach (2017). Preprint. arXiv:1709.02476 Gebru, T., Hoffman, J., Fei-Fei, L.: Fine-grained recognition in the wild: a multi-task domain adaptation approach (2017). Preprint. arXiv:1709.02476
8.
go back to reference Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: European Conference on Computer Vision, pp. 597–613. Springer, Cham (2016) Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: European Conference on Computer Vision, pp. 597–613. Springer, Cham (2016)
9.
go back to reference Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2066–2073. IEEE, Piscataway (2012) Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2066–2073. IEEE, Piscataway (2012)
10.
go back to reference Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 999–1006. IEEE, Piscataway (2011) Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 999–1006. IEEE, Piscataway (2011)
11.
go back to reference Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., Schölkopf, B.: Covariate shift by kernel mean matching. Dataset Shift Mach. Learn. 3(4), 5 (2009) Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., Schölkopf, B.: Covariate shift by kernel mean matching. Dataset Shift Mach. Learn. 3(4), 5 (2009)
12.
go back to reference Hoffman, J., Tzeng, E., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Domain Adaptation in Computer Vision Applications, pp. 173–187. Springer, Cham (2017) Hoffman, J., Tzeng, E., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Domain Adaptation in Computer Vision Applications, pp. 173–187. Springer, Cham (2017)
13.
go back to reference Jhuo, I.H., Liu, D., Lee, D., Chang, S.F.: Robust visual domain adaptation with low-rank reconstruction. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2168–2175. IEEE, Piscataway (2012) Jhuo, I.H., Liu, D., Lee, D., Chang, S.F.: Robust visual domain adaptation with low-rank reconstruction. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2168–2175. IEEE, Piscataway (2012)
14.
go back to reference Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.J., Shamma, D.A.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32–73 (2017) MathSciNetCrossRef Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.J., Shamma, D.A.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32–73 (2017) MathSciNetCrossRef
15.
go back to reference Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
16.
go back to reference LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998) CrossRef LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998) CrossRef
17.
go back to reference Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015) Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
18.
go back to reference Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97–105 (2015) Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97–105 (2015)
19.
go back to reference Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, pp. 136–144 (2016) Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, pp. 136–144 (2016)
20.
go back to reference Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2208–2217 (2017). http://​JMLR.​org Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2208–2217 (2017). http://​JMLR.​org
21.
go back to reference Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008) Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)
22.
go back to reference Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation with multiple sources. In: Advances in Neural Information Processing Systems, pp. 1041–1048 (2009) Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation with multiple sources. In: Advances in Neural Information Processing Systems, pp. 1041–1048 (2009)
23.
go back to reference Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011) Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)
24.
go back to reference Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010) CrossRef Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010) CrossRef
25.
go back to reference Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199–210 (2011) CrossRef Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199–210 (2011) CrossRef
26.
go back to reference Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015) Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
27.
go back to reference Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Computer Vision–ECCV 2010, pp. 213–226 (2010) Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Computer Vision–ECCV 2010, pp. 213–226 (2010)
28.
go back to reference Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation (2017). Preprint. arXiv:1702.08400 Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation (2017). Preprint. arXiv:1702.08400
29.
go back to reference Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation (2017). Preprint. arXiv:1702.05464 Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation (2017). Preprint. arXiv:1702.05464
30.
go back to reference Xie, J., Hu, W., Zhu, S.C., Wu, Y.N.: Learning sparse frame models for natural image patterns. Int. J. Comput. Vis. 114(2–3), 91–112 (2015) MathSciNetMATHCrossRef Xie, J., Hu, W., Zhu, S.C., Wu, Y.N.: Learning sparse frame models for natural image patterns. Int. J. Comput. Vis. 114(2–3), 91–112 (2015) MathSciNetMATHCrossRef
31.
go back to reference Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048–2057 (2015) Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048–2057 (2015)
32.
go back to reference Xu, R., Chen, Z., Zuo, W., Yan, J., Lin, L.: Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3964–3973 (2018) Xu, R., Chen, Z., Zuo, W., Yan, J., Lin, L.: Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3964–3973 (2018)
33.
go back to reference Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: Proceedings of the 15th ACM International Conference on Multimedia, pp. 188–197. ACM, New York (2007) Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: Proceedings of the 15th ACM International Conference on Multimedia, pp. 188–197. ACM, New York (2007)
Metadata
Title
Multi-Source Domain Adaptation by Deep CockTail Networks
Authors
Ziliang Chen
Liang Lin
Copyright Year
2020
DOI
https://doi.org/10.1007/978-3-030-45529-3_12

Premium Partner