Learning Categories From Few Examples With Multi Model Knowledge Transfer

Learning a visual object category from few samples is a compelling and challenging problem. In several real-world applications collecting many annotated data is costly and not always possible. However, a small training set does not allow to cover the high intraclass variability typical of visual objects. In this condition, machine learning methods provide very few guarantees. This paper presents a discriminative model adaptation algorithm able to proficiently learn a target object with few examples by relying on other previously learned source categories. The proposed method autonomously chooses from where and how much to transfer information by solving a convex optimization problem which ensures to have the minimal leave-one-out error on the available training set. We analyze several properties of the described approach and perform an extensive experimental comparison with other existing transfer solutions, consistently showing the value of our algorithm.

[1]  Antonio Torralba,et al.  Transfer Learning by Borrowing Examples for Multiclass Object Detection , 2011, NIPS.

[2]  D. Gans.  The more you know. , 2008, MGMA connexion.

[3]  Thomas Martin Deserno,et al.  Medical Image Annotation in ImageCLEF 2008 , 2008, CLEF.

[4]  Christopher K. I. Williams,et al.  Pascal Visual Object Classes Challenge Results , 2005 .

[5]  Barbara Caputo,et al.  The More You Know, the Less You Learn: From Knowledge Transfer to One-shot Learning of Object Categories , 2009, BMVC.

[6]  Subhabrata Chakraborti,et al.  Nonparametric Statistical Inference , 2011, International Encyclopedia of Statistical Science.

[7]  Don R. Hush,et al.  QP Algorithms with Guaranteed Accuracy and Run Time for Support Vector Machines , 2006, J. Mach. Learn. Res..

[8]  Dit-Yan Yeung,et al.  Transfer metric learning by learning task relationships , 2010, KDD.

[9]  Stefan Kramer,et al.  Kernel-Based Inductive Transfer , 2008, ECML/PKDD.

[10]  Matthieu Guillaumin,et al.  Segmentation Propagation in ImageNet , 2012, ECCV.

[11]  ZissermanAndrew,et al.  The Pascal Visual Object Classes Challenge , 2015 .

[12]  Yi Yao,et al.  Boosting for transfer learning with multiple sources , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Emilio Soria Olivas,et al.  Handbook of Research on Machine Learning Applications and Trends : Algorithms , Methods , and Techniques , 2009 .

[14]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[15]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[16]  Thomas G. Dietterich,et al.  To transfer or not to transfer , 2005, NIPS 2005.

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

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

[19]  Yoram Singer,et al.  Efficient projections onto the l1-ball for learning in high dimensions , 2008, ICML '08.

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

[21]  Barbara Caputo,et al.  Leveraging over prior knowledge for online learning of visual categories , 2012, BMVC.

[22]  Andrew Zisserman,et al.  Enhancing Exemplar SVMs using Part Level Transfer Regularization , 2012, BMVC.

[23]  William-Chandra Tjhi,et al.  Dual Fuzzy-Possibilistic Co-clustering for Document Categorization , 2007 .

[24]  Pedro M. Domingos,et al.  Deep transfer via second-order Markov logic , 2009, ICML '09.

[25]  Charles Cole,et al.  Fluid concepts and creative analogies: Computer models of the fundamental mechanisms of thought , 1996 .

[26]  Sebastian Thrun,et al.  Is Learning The n-th Thing Any Easier Than Learning The First? , 1995, NIPS.

[27]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[28]  Sebastian Nowozin,et al.  On feature combination for multiclass object classification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[29]  Shimon Ullman,et al.  Cross-generalization: learning novel classes from a single example by feature replacement , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[30]  Nathan Intrator,et al.  Making a Low-dimensional Representation Suitable for Diverse Tasks , 1996, Connect. Sci..

[31]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[32]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[33]  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.

[34]  Yoshua Bengio,et al.  Unsupervised and Transfer Learning Challenge: a Deep Learning Approach , 2011, ICML Unsupervised and Transfer Learning.

[35]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[36]  C A Nelson,et al.  Learning to Learn , 2017, Encyclopedia of Machine Learning and Data Mining.

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

[38]  Thomas G. Dietterich,et al.  Improving SVM accuracy by training on auxiliary data sources , 2004, ICML.

[39]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[40]  Michael Goesele,et al.  A shape-based object class model for knowledge transfer , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[41]  Gavriel Salomon,et al.  T RANSFER OF LEARNING , 1992 .

[42]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  M. M. Hassan Mahmud,et al.  Transfer Learning using Kolmogorov Complexity: Basic Theory and Empirical Evaluations , 2007, NIPS.

[44]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[45]  Qiang Yang,et al.  EigenTransfer: a unified framework for transfer learning , 2009, ICML '09.

[46]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

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

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

[49]  André Elisseeff,et al.  Stability and Generalization , 2002, J. Mach. Learn. Res..

[50]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[51]  Trevor Darrell,et al.  Transfer learning for image classification with sparse prototype representations , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[52]  Michael Kohnen,et al.  The IRMA code for unique classification of medical images , 2003, SPIE Medical Imaging.

[53]  Daphna Weinshall,et al.  Exploiting Object Hierarchy: Combining Models from Different Category Levels , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[54]  Peter Stone,et al.  Accelerating Search with Transferred Heuristics , 2007 .

[55]  Fatih Murat Porikli,et al.  Human Detection via Classification on Riemannian Manifolds , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[56]  Ingo Steinwart,et al.  Consistency of support vector machines and other regularized kernel classifiers , 2005, IEEE Transactions on Information Theory.

[57]  Barbara Caputo,et al.  An SVM Confidence-Based Approach to Medical Image Annotation , 2008, CLEF.

[58]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[59]  Michael Fink,et al.  Object Classification from a Single Example Utilizing Class Relevance Metrics , 2004, NIPS.

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

[61]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[62]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[63]  Gavin C. Cawley,et al.  Leave-One-Out Cross-Validation Based Model Selection Criteria for Weighted LS-SVMs , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[64]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.