Domain adaptation is a method to classify the new domain accurately by using the marked image of the old domain. It shows a good but a challenging application prospect in computer vision. In this article, we propose a unified and optimized problem modeling method, which is called as Geodesic Kernel embedding Distribution Alignment (GKDA). Specifically, GKDA aims to reduce the domain differences. GKDA avoids degenerated feature transformation by using geodesic kernel mapping feature, and then adjusts the weight of cross-domain instances in the process of dimensionality reduction in principle, finally, constructs a new feature to represent the difference of distribution and unrelated instances. The experiment result shows that GKDA has obvious superiority in cross-domain image recognition.
PanS.J. and YangQ., A survey on transfer learning, IEEE Transactions on Knowledge and Data Engineering22(10) (2009), 1345–1359.
2.
WangJ. et al., Everything about Transfer Learning and Domain Adapation, http://transferlearning.xyz, 2018.
3.
AndreasA.EvgeniouT. and PontilM., Multi-task feature learning, Advances in Neural Information Processing Systems, 2007, pp. 41–48.
4.
BruzzoneL. and MarconciniM., Domain adaptation problems: A DASVM classification technique and a circular validation strategy, IEEE Transactions on Pattern Analysis and Machine Intelligence32(5) (2009), 770–787.
5.
ChenM.WeinbergerK.Q. and BlitzerJ.C., Co-training for domain adaptation, In Advances in Neural Information Processing Systems (2011), 2456–2464.
6.
Ben-DavidS.BlitzerJ.CrammerK. and PereiraF., Analysis of representations for domain adaptation, In Advances in Neural Information Processing Systems (2007), 137–144.
7.
ChuW.S.De la TorreF. and CohnJ.F., Selective transfer machine for personalized facial action unit detection, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 3515–3522.
8.
GopalanR.LiR. and ChellappaR., Domain adaptation for object recognition: An unsupervised approach, In 2011 International Conference on Computer Vision, 2011, pp. 999–1006.
9.
GuQ.LiZ. and HanJ., Joint feature selection and subspace learning, In Twenty-Second International Joint Conference on Artificial Intelligence, 2011, pp. 1294–1299.
10.
GrettonA.BorgwardtK.RaschM.SchölkopfB. and SmolaA.J., A kernel method for the two-sample-problem, In Advances in Neural Information Processing Systems, 2007, pp. 513–520.
11.
HuangJ.GrettonA.BorgwardtK.SchölkopfB. and SmolaA.J., Correcting sample selection bias by unlabeled data, In Advances in Neural Information Processing Systems, 2007, pp. 601–608.
12.
WangJ.FengW.ChenY.YuH.HuangM. and YuP.S., Visual domain adaptation with manifold embedded distribution alignment, In 2018 ACM Multimedia Conference on Multimedia Conference, 2018, pp. 402–410.
13.
FernandoB.HabrardA.SebbanM. and TuytelaarsT., Unsupervised visual domain adaptation using subspace alignment, In Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2960–2967.
14.
LongM.DingG.WangJ.SunJ.GuoY. and YuP.S., Transfer sparse coding for robust image representation, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 407–414.
15.
GongB.ShiY.ShaF. and GraumanK., Geodesic flow kernel for unsupervised domain adaptation, In 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2066–2073.
16.
SunB. and SaenkoK., Deep CORAL: Correlation Alignment for Deep Domain Adaptation, Computer Vision – ECCV 2016 Workshops, 2016, pp. 443–450.
17.
ZhangJ.LiW. and OgunbonaP., Joint geometrical and statistical alignment for visual domain adaptation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1859–1867.
18.
GhifaryM.BalduzziD.KleijnW.B. and ZhangM., Scatter component analysis: A unified framework for domain adaptation and domain generalization, IEEE Transactions on Pattern Analysis and Machine Intelligence39(7) (2016), 1414–1430.
19.
PanS.J.KwokJ.T. and YangQ., Transfer Learning via Dimensionality Reduction, in AAAI8 (2008), 677–682.
20.
PanS.J.TsangI.W.KwokJ.T. and YangQ., Domain adaptation via transfer component analysis, IEEE Transactions on Neural Networks22(2) (2010), 199–210.
21.
SunB.FengJ. and SaenkoK., Return of frustratingly easy domain adaptation, In Thirtieth AAAI Conference on Artificial Intelligence, 2016, pp. 2058–2065.
22.
LongM.WangJ.DingG. et al., Adaptation regularization: A general framework for transfer learning, IEEE Transactions on Knowledge and Data Engineering26(5) (2013), 1076–1089.
23.
LongM.WangJ.DingG. et al., Transfer feature learning with joint distribution adaptation, In Proceedings of the IEEE International Conference on Computer vision, 2013, pp. 2200–2207.
24.
LongM.WangJ.DingG. et al., Transfer joint matching for unsupervised domain adaptation, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1410–1417.
25.
BelkinM.NiyogiP. and SindhwaniV., Manifold regularization: A geometric framework for learning from labeled and unlabeled examples, Journal of Machine Learning Research7 (2006), 2399–2434.
26.
HammJ. and LeeD.D., Grassmann discriminant analysis: a unifying view on subspace-based learning, In Proceedings of the 25th International Conference on Machine Learning, 2008, pp. 376–383.
27.
XuY. et al., A unified framework for metric transfer learning, IEEE Transactions on Knowledge and Data Engineering29(6) (2017), 1158–1171.
28.
ChenC. et al., Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation, AAAI Technical Track: Machine Learning, 2019, pp. 3296–3303.
29.
LiJ. et al., Transfer independently together: A generalized framework for domain adaptation, IEEE Transactions on Cybernetics49(6) (2018), 2144–2155.
30.
WeiJ. et al., Learning Discriminative Geodesic Flow Kernel for Unsupervised Domain Adaptation, 2018 IEEE International Conference on Multimedia and Expo (ICME) IEEE, 2018, pp. 1–6.
31.
CourtyN. et al., Optimal transport for domain adaptation, IEEE Transactions on Pattern Analysis and Machine Intelligence39(9) (2016), 1853–1865.
32.
JindongW. et al., Easy transfer learning by exploiting intra-domain structures, 2019 IEEE International Conference on Multimedia and Expo (ICME), 2019.
