Transfer Joint Matching for Unsupervised Domain Adaptation

Visual domain adaptation, which learns an accurate classifier for a new domain using labeled images from an old domain, has shown promising value in computer vision yet still been a challenging problem. Most prior works have explored two learning strategies independently for domain adaptation: feature matching and instance reweighting. In this paper, we show that both strategies are important and inevitable when the domain difference is substantially large. We therefore put forward a novel Transfer Joint Matching (TJM) approach to model them in a unified optimization problem. Specifically, TJM aims to reduce the domain difference by jointly matching the features and reweighting the instances across domains in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances. Comprehensive experimental results verify that TJM can significantly outperform competitive methods for cross-domain image recognition problems.

[1]  Rama Chellappa,et al.  Domain Adaptive Dictionary Learning , 2012, ECCV.

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

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

[4]  Matthieu Guillaumin,et al.  Large-scale knowledge transfer for object localization in ImageNet , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[6]  Qi Tian,et al.  Multi-feature metric learning with knowledge transfer among semantics and social tagging , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Christoph H. Lampert,et al.  Weakly-Paired Maximum Covariance Analysis for Multimodal Dimensionality Reduction and Transfer Learning , 2010, ECCV.

[8]  Rama Chellappa,et al.  Domain adaptation for object recognition: An unsupervised approach , 2011, 2011 International Conference on Computer Vision.

[9]  Andrew Zisserman,et al.  Tabula rasa: Model transfer for object category detection , 2011, 2011 International Conference on Computer Vision.

[10]  Feiping Nie,et al.  Efficient and Robust Feature Selection via Joint ℓ2, 1-Norms Minimization , 2010, NIPS.

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

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

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

[14]  Tao Mei,et al.  SocialTransfer: cross-domain transfer learning from social streams for media applications , 2012, ACM Multimedia.

[15]  Massimiliano Pontil,et al.  Multi-Task Feature Learning , 2006, NIPS.

[16]  Barbara Caputo,et al.  Multiclass transfer learning from unconstrained priors , 2011, 2011 International Conference on Computer Vision.

[17]  Philip S. Yu,et al.  Transfer Sparse Coding for Robust Image Representation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Jennifer G. Dy,et al.  From Transformation-Based Dimensionality Reduction to Feature Selection , 2010, ICML.

[19]  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.

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

[21]  Christoph H. Lampert,et al.  Learning to detect unseen object classes by between-class attribute transfer , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Fernando De la Torre,et al.  Selective Transfer Machine for Personalized Facial Action Unit Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Feiping Nie,et al.  Dyadic transfer learning for cross-domain image classification , 2011, 2011 International Conference on Computer Vision.

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

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

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

[27]  Jiawei Han,et al.  Joint Feature Selection and Subspace Learning , 2011, IJCAI.