Learning with few examples for binary and multiclass classification using regularization of randomized trees

The human visual system is often able to learn to recognize difficult object categories from only a single view, whereas automatic object recognition with few training examples is still a challenging task. This is mainly due to the human ability to transfer knowledge from related classes. Therefore, an extension to Randomized Decision Trees is introduced for learning with very few examples by exploiting interclass relationships. The approach consists of a maximum a posteriori estimation of classifier parameters using a prior distribution learned from similar object categories. Experiments on binary and multiclass classification tasks show significant performance gains

[1]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[3]  Misha Elena Kilmer,et al.  Choosing Regularization Parameters in Iterative Methods for Ill-Posed Problems , 2000, SIAM J. Matrix Anal. Appl..

[4]  Raphaël Marée,et al.  Random subwindows for robust image classification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Li Fei-Fei.  Knowledge transfer in learning to recognize visual objects classes , 2006 .

[8]  Antonio Torralba,et al.  Statistics of natural image categories , 2003, Network.

[9]  Michael Fink.  Object Classication from a Single Example Utilizing Class Relevance Pseudo-Metrics , 2004, NIPS 2004.

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

[11]  Daphne Koller,et al.  Learning a meta-level prior for feature relevance from multiple related tasks , 2007, ICML '07.

[12]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[13]  Alan F. Murray,et al.  International Joint Conference on Neural Networks , 1993 .

[14]  Bernt Schiele,et al.  What Helps Where \textendash And Why? Semantic Relatedness for Knowledge Transfer , 2010, CVPR 2010.

[15]  Shimon Ullman,et al.  From Aardvark to Zorro: A Benchmark for Mammal Image Classification , 2008, International Journal of Computer Vision.

[16]  Cordelia Schmid,et al.  A Discriminative Framework for Texture and Object Recognition Using Local Image Features , 2006, Toward Category-Level Object Recognition.

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

[18]  Paul A. Viola,et al.  Learning from one example through shared densities on transforms , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

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

[20]  Cordelia Schmid,et al.  Semi-Local Affine Parts for Object Recognition , 2004, BMVC.

[21]  Frédéric Jurie,et al.  Fast Discriminative Visual Codebooks using Randomized Clustering Forests , 2006, NIPS.

[22]  Christophe G. Giraud-Carrier,et al.  Transfer Learning in Decision Trees , 2007, 2007 International Joint Conference on Neural Networks.

[23]  Vincent Lepetit,et al.  Randomized trees for real-time keypoint recognition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[24]  Derek Hoiem,et al.  3D LayoutCRF for Multi-View Object Class Recognition and Segmentation , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  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).

[26]  Trevor Darrell,et al.  Learning Visual Representations using Images with Captions , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Edwin V. Bonilla,et al.  Multi-task Gaussian Process Prediction , 2007, NIPS.

[28]  Joachim Denzler,et al.  Challenging Anomaly Detection in Wire Ropes Using Linear Prediction Combined with One-class Classification , 2008, VMV.

[29]  Linda B. Smith,et al.  The place of perception in children's concepts ☆ , 1993 .

[30]  Bernt Schiele,et al.  What helps where – and why? Semantic relatedness for knowledge transfer , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[31]  Roberto Cipolla,et al.  Semantic texton forests for image categorization and segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[33]  Joachim Denzler,et al.  Learning with Few Examples using a Constrained Gaussian Prior on Randomized Trees , 2008, VMV.

[34]  Thomas Hofmann,et al.  Fast Discriminative Visual Codebooks using Randomized Clustering Forests , 2007 .

[35]  GeversTheo,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010 .