Learning with Few Examples by Transferring Feature Relevance

The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use of feature relevance as prior information from similar binary classification tasks. An approach is presented which is capable to use this information to increase the recognition performance for learning with few examples on a new binary classification task. Feature relevance probabilities are estimated by a randomized decision forest of a related task and used as a prior distribution in the construction of a new forest. Experiments in an image categorization scenario show a significant performance gain in the case of few training examples.

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

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

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

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

[5]  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).

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

[7]  Yair Weiss,et al.  Learning From a Small Number of Training Examples by Exploiting Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

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

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

[10]  Steve R. Gunn,et al.  Identifying Feature Relevance Using a Random Forest , 2005, SLSFS.

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

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

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

[14]  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.

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

[16]  Masoud Nikravesh,et al.  Feature Extraction: Foundations and Applications (Studies in Fuzziness and Soft Computing) , 2006 .

[17]  Masoud Nikravesh,et al.  Feature Extraction - Foundations and Applications , 2006, Feature Extraction.

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