Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning. However, there are two significant challenges: (1) degenerated feature transformation, which means that distribution alignment is often performed in the original feature space, where feature distortions are hard to overcome. On the other hand, subspace learning is not sufficient to reduce the distribution divergence. (2) unevaluated distribution alignment, which means that existing distribution alignment methods only align the marginal and conditional distributions with equal importance, while they fail to evaluate the different importance of these two distributions in real applications. In this paper, we propose a Manifold Embedded Distribution Alignment (MEDA) approach to address these challenges. MEDA learns a domain-invariant classifier in Grassmann manifold with structural risk minimization, while performing dynamic distribution alignment to quantitatively account for the relative importance of marginal and conditional distributions. To the best of our knowledge, MEDA is the first attempt to perform dynamic distribution alignment for manifold domain adaptation. Extensive experiments demonstrate that MEDA shows significant improvements in classification accuracy compared to state-of-the-art traditional and deep methods.

[1]  E. Denman,et al.  The matrix sign function and computations in systems , 1976 .

[2]  James Parker,et al.  on Knowledge and Data Engineering, , 1990 .

[3]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

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

[5]  NiyogiPartha,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006 .

[6]  Qiang Yang,et al.  Boosting for transfer learning , 2007, ICML '07.

[7]  Daniel D. Lee,et al.  Grassmann discriminant analysis: a unifying view on subspace-based learning , 2008, ICML '08.

[8]  Jun Huan,et al.  Large margin transductive transfer learning , 2009, CIKM.

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

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

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

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

[13]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

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

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Ye Xu,et al.  Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias , 2013, 2013 IEEE International Conference on Computer Vision.

[17]  Tinne Tuytelaars,et al.  Unsupervised Visual Domain Adaptation Using Subspace Alignment , 2013, 2013 IEEE International Conference on Computer Vision.

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

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

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

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

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

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

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

[25]  Rémi Emonet,et al.  Landmarks-based kernelized subspace alignment for unsupervised domain adaptation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Kate Saenko,et al.  Subspace Distribution Alignment for Unsupervised Domain Adaptation , 2015, BMVC.

[27]  Philip S. Yu,et al.  Domain Invariant Transfer Kernel Learning , 2015, IEEE Transactions on Knowledge and Data Engineering.

[28]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

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

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

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

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

[33]  Mehrtash Tafazzoli Harandi,et al.  Distribution-Matching Embedding for Visual Domain Adaptation , 2016, J. Mach. Learn. Res..

[34]  Qingming Huang,et al.  Deep Unsupervised Convolutional Domain Adaptation , 2017, ACM Multimedia.

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

[36]  Mengjie Zhang,et al.  Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Hui Xiong,et al.  A Unified Framework for Metric Transfer Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[38]  Jing Zhang,et al.  Joint Geometrical and Statistical Alignment for Visual Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Henning Müller,et al.  Datasets column: diversity and credibility for social images and image retrieval , 2018, ACMMR.

[40]  Jianmin Wang,et al.  Unsupervised Domain Adaptation With Distribution Matching Machines , 2018, AAAI.

[41]  Wei Liu,et al.  Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.