Generalized Domain-Adaptive Dictionaries

Data-driven dictionaries have produced state-of-the-art results in various classification tasks. However, when the target data has a different distribution than the source data, the learned sparse representation may not be optimal. In this paper, we investigate if it is possible to optimally represent both source and target by a common dictionary. Specifically, we describe a technique which jointly learns projections of data in the two domains, and a latent dictionary which can succinctly represent both the domains in the projected low-dimensional space. An efficient optimization technique is presented, which can be easily kernelized and extended to multiple domains. The algorithm is modified to learn a common discriminative dictionary, which can be further used for classification. The proposed approach does not require any explicit correspondence between the source and target domains, and shows good results even when there are only a few labels available in the target domain. Various recognition experiments show that the method performs on par or better than competitive state-of-the-art methods.

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

[2]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[3]  David W. Jacobs,et al.  Generalized Multiview Analysis: A discriminative latent space , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Ioannis Gkioulekas,et al.  Dimensionality Reduction Using the Sparse Linear Model , 2011, NIPS.

[5]  Jean Ponce,et al.  Task-Driven Dictionary Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Trevor Darrell,et al.  What you saw is not what you get: Domain adaptation using asymmetric kernel transforms , 2011, CVPR 2011.

[7]  Guillermo Sapiro,et al.  Classification and clustering via dictionary learning with structured incoherence and shared features , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[9]  Thomas S. Huang,et al.  Coupled Dictionary Training for Image Super-Resolution , 2012, IEEE Transactions on Image Processing.

[10]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[11]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[12]  Yueting Zhuang,et al.  Sparse Unsupervised Dimensionality Reduction for Multiple View Data , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Hal Daumé,et al.  Frustratingly Easy Domain Adaptation , 2007, ACL.

[14]  Wotao Yin,et al.  A feasible method for optimization with orthogonality constraints , 2013, Math. Program..

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

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

[17]  David Zhang,et al.  On the Dimensionality Reduction for Sparse Representation Based Face Recognition , 2010, 2010 20th International Conference on Pattern Recognition.

[18]  Quan Pan,et al.  Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[20]  David Zhang,et al.  Fisher Discrimination Dictionary Learning for sparse representation , 2011, 2011 International Conference on Computer Vision.

[21]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

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

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

[24]  D. Jacobs,et al.  Bypassing synthesis: PLS for face recognition with pose, low-resolution and sketch , 2011, CVPR 2011.

[25]  Trevor Darrell,et al.  Factorized Latent Spaces with Structured Sparsity , 2010, NIPS.

[26]  Rama Chellappa,et al.  Sparse Embedding: A Framework for Sparsity Promoting Dimensionality Reduction , 2012, ECCV.

[27]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

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

[30]  Rama Chellappa,et al.  Learning discriminative dictionaries with partially labeled data , 2012, 2012 19th IEEE International Conference on Image Processing.