PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories

This paper introduces a probabilistic latent variable model to address unsupervised domain adaptation problems. Specifically, we tackle the task of categorization of visual input from different domains by learning projections from each domain to a latent (shared) space jointly with the classifier in the latent space, which simultaneously minimizes the domain disparity while maximizing the classifier's discriminative power. Furthermore, the non-parametric nature of our adaptation model makes it possible to infer the latent space dimension automatically from data. We also develop a novel regularized Variational Bayes (VB) algorithm for efficient estimation of the model parameters. We compare the proposed model with the state-of-the-art methods for the tasks of visual domain adaptation using both handcrafted and deep-net features. Our experiments show that even with a simple softmax classifier, our model outperforms several state-of-the-art methods that take advantage of more sophisticated classification schemes.

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

[2]  Renato Renner,et al.  Smooth Renyi entropy and applications , 2004, International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings..

[3]  Mengjie Zhang,et al.  Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation , 2016, ECCV.

[4]  Mehrtash Tafazzoli Harandi,et al.  Learning an Invariant Hilbert Space for Domain Adaptation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Avishek Saha,et al.  Co-regularization Based Semi-supervised Domain Adaptation , 2010, NIPS.

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

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

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

[9]  Zoubin Ghahramani,et al.  Variational Inference for Bayesian Mixtures of Factor Analysers , 1999, NIPS.

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

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

[12]  Shih-Fu Chang,et al.  Cross-domain learning methods for high-level visual concept classification , 2008, 2008 15th IEEE International Conference on Image Processing.

[13]  Hans-Peter Kriegel,et al.  Integrating structured biological data by Kernel Maximum Mean Discrepancy , 2006, ISMB.

[14]  Guillaume Bouchard.  Efficient Bounds for the Softmax Function and Applications to Approximate Inference in Hybrid models , 2008 .

[15]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Yu-Chiang Frank Wang,et al.  Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[19]  Min Xiao,et al.  Feature Space Independent Semi-Supervised Domain Adaptation via Kernel Matching , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

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

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

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

[24]  Namil Kim,et al.  Pixel-Level Domain Transfer , 2016, ECCV.

[25]  Thomas L. Griffiths,et al.  Infinite latent feature models and the Indian buffet process , 2005, NIPS.

[26]  Roland Kuhn,et al.  Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation , 2010, EMNLP.

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

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

[29]  Rong Yan,et al.  Adapting SVM Classifiers to Data with Shifted Distributions , 2007 .

[30]  Ivor W. Tsang,et al.  Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Michael I. Jordan,et al.  Hierarchical Beta Processes and the Indian Buffet Process , 2007, AISTATS.

[32]  Shaogang Gong,et al.  Unsupervised Domain Adaptation for Zero-Shot Learning , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[33]  Trevor Darrell,et al.  Semi-supervised Domain Adaptation with Instance Constraints , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Shiguang Shan,et al.  Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[35]  Motoaki Kawanabe,et al.  Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation , 2007, NIPS.

[36]  Philip S. Yu,et al.  Deep Learning of Transferable Representation for Scalable Domain Adaptation , 2016, IEEE Transactions on Knowledge and Data Engineering.

[37]  Yu-Chiang Frank Wang,et al.  Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[38]  Michael I. Jordan,et al.  Unsupervised Domain Adaptation with Residual Transfer Networks , 2016, NIPS.

[39]  Chulhee Lee,et al.  Feature extraction based on the Bhattacharyya distance , 2003, Pattern Recognit..

[40]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[41]  Rama Chellappa,et al.  Visual Domain Adaptation: A survey of recent advances , 2015, IEEE Signal Processing Magazine.

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

[43]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

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

[47]  H. Shimodaira,et al.  Improving predictive inference under covariate shift by weighting the log-likelihood function , 2000 .

[48]  ChengXiang Zhai,et al.  Instance Weighting for Domain Adaptation in NLP , 2007, ACL.

[49]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.