Towards autonomous bootstrapping for life-long learning categorization tasks

We present an exemplar-based learning approach for incremental and life-long learning of visual categories. The basic concept of the proposed learning method is to subdivide the learning process into two phases. In the first phase we utilize supervised learning to generate an appropriate category seed, while in the second phase this seed is used to autonomously bootstrap the visual representation. This second learning phase is especially useful for assistive systems like a mobile robot, because the visual knowledge can be enhanced even if no tutor is present. Although for this autonomous bootstrapping no category labels are provided, we argue that contextual information is beneficial for this process. Finally we investigate the effect of the proposed second learning phase with respect to the overall categorization performance.

[1]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[2]  Gökhan Tür,et al.  Combining active and semi-supervised learning for spoken language understanding , 2005, Speech Commun..

[3]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[4]  B. Schiele,et al.  Combined Object Categorization and Segmentation With an Implicit Shape Model , 2004 .

[5]  Andrew McCallum,et al.  Employing EM and Pool-Based Active Learning for Text Classification , 1998, ICML.

[6]  Craig A. Knoblock,et al.  Active + Semi-supervised Learning = Robust Multi-View Learning , 2002, ICML.

[7]  Horst-Michael Groß,et al.  A vision architecture for unconstrained and incremental learning of multiple categories , 2009, Memetic Comput..

[8]  Heiko Wersing,et al.  A biologically motivated visual memory architecture for online learning of objects , 2008, Neural Networks.

[9]  R. French.  Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.

[10]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[11]  R. French,et al.  Catastrophic Forgetting in Connectionist Networks: Causes, Consequences and Solutions , 1994 .

[12]  Thomas Villmann,et al.  Generalized relevance learning vector quantization , 2002, Neural Networks.

[13]  Ronald Rosenfeld,et al.  Semi-supervised learning with graphs , 2005 .

[14]  Bernt Schiele,et al.  Multiple Object Class Detection with a Generative Model , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[15]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Thomas Serre,et al.  Categorization by Learning and Combining Object Parts , 2001, NIPS.

[17]  Heiko Wersing,et al.  A Comparison of Features in Parts-Based Object Recognition Hierarchies , 2007, ICANN.

[18]  Erzsébet Merényi,et al.  GENERALIZED RELEVANCE LEARNING VECTOR QUANTIZATION FOR CLASSIFICATION-DRIVEN FEATURE EXTRACTION FROM HYPERSPECTRAL DATA , 2006 .

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

[20]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .