A vision architecture for unconstrained and incremental learning of multiple categories

We present an integrated vision architecture capable of incrementally learning several visual categories based on natural hand-held objects. Additionally we focus on interactive learning, which requires real-time image processing methods and a fast learning algorithm. The overall system is composed of a figure-ground segregation part, several feature extraction methods and a life-long learning approach combining incremental learning with category-specific feature selection. In contrast to most visual categorization approaches, where typically each view is assigned to a single category, we allow labeling with an arbitrary number of shape and color categories. We also impose no restrictions on the viewing angle of presented objects, relaxing the common constraint on canonical views.

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

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

[3]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[4]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Heiko Wersing,et al.  Online Learning of Objects in a Biologically Motivated Visual Architecture , 2007, Int. J. Neural Syst..

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

[7]  Michael Biehl,et al.  Relevance matrices in LVQ , 2007, ESANN.

[8]  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).

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

[10]  A.M. Arsenic,et al.  Developmental learning on a humanoid robot , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[11]  Lixin Fan,et al.  Categorizing Nine Visual Classes using Local Appearance Descriptors , 2004 .

[12]  Bernt Schiele,et al.  Cross‐modal Learning of Visual Categories using Different Levels of Supervision , 2007, ICVS 2007.

[13]  Sebastian Lang,et al.  Improving adaptive skin color segmentation by incorporating results from face detection , 2002, Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication.

[14]  Fred Henrik Hamker,et al.  Life-long learning Cell Structures--continuously learning without catastrophic interference , 2001, Neural Networks.

[15]  Luc Van Gool,et al.  Towards Multi-View Object Class Detection , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Shen Furao,et al.  An incremental network for on-line unsupervised classification and topology learning , 2006, Neural Networks.

[17]  Luc Steels,et al.  Aibo''s first words. the social learning of language and meaning. Evolution of Communication , 2002 .

[18]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[19]  Horst Bischof,et al.  On-line Learning of Unknown Hand Held Objects via Tracking , 2006 .

[20]  B Fritzke,et al.  A growing neural gas network learns topologies. G. Tesauro, DS Touretzky, and TK Leen, editors , 1995, NIPS 1995.

[21]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[22]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

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

[24]  Danijel Skocaj,et al.  Continuous Learning of Simple Visual Concepts Using Incremental Kernel Density Estimation , 2016, VISAPP.

[25]  Heiko Wersing,et al.  Online figure-ground segmentation with adaptive metrics in generalized LVQ , 2009, Neurocomputing.

[26]  Horst-Michael Groß,et al.  A Vector Quantization Approach for Life-Long Learning of Categories , 2008, ICONIP.

[27]  Heiko Wersing,et al.  Biologically motivated visual behaviors for humanoids: Learning to interact and learning in interaction , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[28]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[29]  Shigeo Abe,et al.  Incremental learning of feature space and classifier for face recognition , 2005, Neural Networks.

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

[31]  Nick Hawes,et al.  A System for Continuous Learning of Visual Concepts , 2007 .

[32]  Heiko Wersing,et al.  Learning Optimized Features for Hierarchical Models of Invariant Object Recognition , 2003, Neural Computation.

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

[34]  Horst-Michael Groß,et al.  Biological neural architecture for chromatic adaptation resulting in constant color sensations , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).