One-Shot Learning of Object Categories Using Dependent Gaussian Processes

Knowledge transfer from related object categories is a key concept to allow learning with few training examples. We present how to use dependent Gaussian processes for transferring knowledge from a related category in a non-parametric Bayesian way. Our method is able to select this category automatically using efficient model selection techniques. We show how to optionally incorporate semantic similarities obtained from the hierarchical lexical database WordNet [1] into the selection process. The framework is applied to image categorization tasks using state-of-the-art image-based kernel functions. A large scale evaluation shows the benefits of our approach compared to independent learning and a SVM based approach.

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

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

[3]  Trevor Darrell,et al.  Gaussian Processes for Object Categorization , 2010, International Journal of Computer Vision.

[4]  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).

[5]  M. Birkner,et al.  Blow-up of semilinear PDE's at the critical dimension. A probabilistic approach , 2002 .

[6]  C. Rasmussen,et al.  Approximations for Binary Gaussian Process Classification , 2008 .

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

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

[9]  Kian Ming Adam Chai.  Generalization Errors and Learning Curves for Regression with Multi-task Gaussian Processes , 2009, NIPS.

[10]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[11]  Thomas G. Dietterich.  Adaptive computation and machine learning , 1998 .

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

[13]  Cordelia Schmid,et al.  Semantic Hierarchies for Visual Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Giuseppe De Nicolao,et al.  Bayesian Online Multitask Learning of Gaussian Processes , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  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.

[16]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[17]  Ted Pedersen,et al.  WordNet::Similarity - Measuring the Relatedness of Concepts , 2004, NAACL.

[18]  J. Kiefer,et al.  Sequential minimax search for a maximum , 1953 .

[19]  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.

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

[21]  Neil D. Lawrence,et al.  Transferring Nonlinear Representations using Gaussian Processes with a Shared Latent Space , 2008 .

[22]  Qiang Yang,et al.  Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI-10) Adaptive Transfer Learning , 2022 .

[23]  R. Mooney,et al.  Schema acquisition from a single example , 1992 .

[24]  Neil D. Lawrence,et al.  Extensions of the Informative Vector Machine , 2004, Deterministic and Statistical Methods in Machine Learning.

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