Compact Cluster-based Balanced Distribution Adaptation for Transfer Learning

Recently, Domain Adaptation has received great attention in addressing domain shift problem, where source domain and target domain follow different distribution. Existing methods often seek to minimize the marginal distribution and the conditional distribution across domains however treat them equally, which is not reasonable in real applications. Moreover, it is easy to misclassify on target data with large within-class scatter. In this paper, we propose a Compact Cluster-based Balanced Distribution Adaptation (CC-BDA) method for cross-domain classification. CC-BDA exploits the balanced domain adaptation by increasing the balance factor dynamically in each iteration until convergence. In addition, we construct compact clusters to reduce within-class scatter alongside the domain adaptation, which endows samples with the same label much closer from their means. Finally, we present analysis and performance evaluation over seven state-of-the-art baseline methods. The results show that CC-BDA significantly outperforms other adaptation methods in accuracy and execution time cost.

[1]  Sethuraman Panchanathan,et al.  A Two-Stage Weighting Framework for Multi-Source Domain Adaptation , 2011, NIPS.

[2]  Ramesh Nallapati,et al.  A Comparative Study of Methods for Transductive Transfer Learning , 2007, Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007).

[3]  Rama Chellappa,et al.  Unsupervised Adaptation Across Domain Shifts by Generating Intermediate Data Representations , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Zhiguo Cao,et al.  An Embarrassingly Simple Approach to Visual Domain Adaptation , 2018, IEEE Transactions on Image Processing.

[5]  Brian C. Lovell,et al.  Unsupervised Domain Adaptation by Domain Invariant Projection , 2013, 2013 IEEE International Conference on Computer Vision.

[6]  Qilong Wang,et al.  Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Qiang Yang,et al.  Distant Domain Transfer Learning , 2017, AAAI.

[8]  Jaime G. Carbonell,et al.  Feature Selection for Transfer Learning , 2011, ECML/PKDD.

[9]  Yu-Chiang Frank Wang,et al.  Unsupervised Domain Adaptation With Label and Structural Consistency , 2016, IEEE Transactions on Image Processing.

[10]  Qiang Yang,et al.  Transfer Learning via Dimensionality Reduction , 2008, AAAI.

[11]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Philip S. Yu,et al.  Transfer Joint Matching for Unsupervised Domain Adaptation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[14]  Jafar Tahmoresnezhad,et al.  Visual domain adaptation via transfer feature learning , 2017, Knowledge and Information Systems.

[15]  Dong Liu,et al.  Robust visual domain adaptation with low-rank reconstruction , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

[17]  Yiqiang Chen,et al.  Balanced Distribution Adaptation for Transfer Learning , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[18]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[19]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[20]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[21]  Deepak S. Turaga,et al.  Cross domain distribution adaptation via kernel mapping , 2009, KDD.

[22]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.