Domain Invariant and Class Discriminative Feature Learning for Visual Domain Adaptation

Domain adaptation manages to build an effective target classifier or regression model for unlabeled target data by utilizing the well-labeled source data but lying different distributions. Intuitively, to address domain shift problem, it is crucial to learn domain invariant features across domains, and most existing approaches have concentrated on it. However, they often do not directly constrain the learned features to be class discriminative for both source and target data, which is of vital importance for the final classification. Therefore, in this paper, we put forward a novel feature learning method for domain adaptation to construct both domain invariant and class discriminative representations, referred to as DICD. Specifically, DICD is to learn a latent feature space with important data properties preserved, which reduces the domain difference by jointly matching the marginal and class-conditional distributions of both domains, and simultaneously maximizes the inter-class dispersion and minimizes the intra-class scatter as much as possible. Experiments in this paper have demonstrated that the class discriminative properties will dramatically alleviate the cross-domain distribution inconsistency, which further boosts the classification performance. Moreover, we show that exploring both domain invariance and class discriminativeness of the learned representations can be integrated into one optimization framework, and the optimal solution can be derived effectively by solving a generalized eigen-decomposition problem. Comprehensive experiments on several visual cross-domain classification tasks verify that DICD can outperform the competitors significantly.

[1]  Sameer A. Nene,et al.  Columbia Object Image Library (COIL100) , 1996 .

[2]  Brian C. Lovell,et al.  Domain Adaptation on the Statistical Manifold , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Cheng Wu,et al.  Semi-Supervised and Unsupervised Extreme Learning Machines , 2014, IEEE Transactions on Cybernetics.

[4]  Xuelong Li,et al.  Discriminative Transfer Subspace Learning via Low-Rank and Sparse Representation , 2016, IEEE Transactions on Image Processing.

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

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

[7]  Yun Fu,et al.  Robust Transfer Metric Learning for Image Classification , 2017, IEEE Transactions on Image Processing.

[8]  Dacheng Tao,et al.  Bregman Divergence-Based Regularization for Transfer Subspace Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[9]  Jiwen Lu,et al.  Deep transfer metric learning , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[11]  John Blitzer,et al.  Co-Training for Domain Adaptation , 2011, NIPS.

[12]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Computing k-Nearest Neighbors , 1975, IEEE Transactions on Computers.

[13]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[14]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[15]  Kristen Grauman,et al.  Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation , 2013, ICML.

[16]  Jian Yang,et al.  Instance Selection and Instance Weighting for Cross-Domain Sentiment Classification via PU Learning , 2013, IJCAI.

[17]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[18]  Fanjiang Xu,et al.  Cross-Domain Metric Learning Based on Information Theory , 2014, AAAI.

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

[20]  Peng Cui,et al.  On Image Classification: Correlation v.s. Causality , 2017, ArXiv.

[21]  David Zhang,et al.  LSDT: Latent Sparse Domain Transfer Learning for Visual Adaptation , 2016, IEEE Transactions on Image Processing.

[22]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[23]  Ming Shao,et al.  Generalized Transfer Subspace Learning Through Low-Rank Constraint , 2014, International Journal of Computer Vision.

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

[25]  Rong Yan,et al.  Cross-domain video concept detection using adaptive svms , 2007, ACM Multimedia.

[26]  Ivor W. Tsang,et al.  Domain Transfer Multiple Kernel Learning , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

[28]  Lorenzo Bruzzone,et al.  Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[30]  Daoqiang Zhang,et al.  Semi-Supervised Dimensionality Reduction ∗ , 2007 .

[31]  Bernhard Schölkopf,et al.  Correcting Sample Selection Bias by Unlabeled Data , 2006, NIPS.

[32]  Gao Huang,et al.  Prediction Reweighting for Domain Adaptation , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Bo Geng,et al.  DAML: Domain Adaptation Metric Learning , 2011, IEEE Transactions on Image Processing.

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

[35]  Philip S. Yu,et al.  Adaptation Regularization: A General Framework for Transfer Learning , 2014, IEEE Transactions on Knowledge and Data Engineering.

[36]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[37]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression (PIE) database , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

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

[39]  Yiming Yang,et al.  Cross-Domain Kernel Induction for Transfer Learning , 2017, AAAI.

[40]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

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

[42]  Trevor Darrell,et al.  Efficient Learning of Domain-invariant Image Representations , 2013, ICLR.

[43]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[44]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

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

[46]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[47]  Shaowei Liu,et al.  General Knowledge Embedded Image Representation Learning , 2018, IEEE Transactions on Multimedia.

[48]  Euntai Kim,et al.  A new weighted approach to imbalanced data classification problem via support vector machine with quadratic cost function , 2011, Expert Syst. Appl..