Top-down visual selective attention model combined with bottom-up saliency map for incremental object perception

Humans can efficiently perceive arbitrary visual objects based on incremental learning mechanism and selective attention function. In this paper, we propose a new top-down attention model based on human visual attention mechanism, which considers both relative feature based bottom-up saliency and goal oriented top-down attention. The proposed model can generate top-down bias signals of form and color features for a specific object, which draw attention to find a desired object by an incremental learning mechanism together with object feature representation scheme. A growing fuzzy topology adaptive resonance theory (GFTART) model is proposed by adapting a growing cell structure (GCS) unit into a conventional fuzzy ART, by which the proliferation problem of the conventional fuzzy ART can be enhanced. The proposed GFTART plays two important roles for object color and form biased attention; one is to incrementally learn and memorize color and form features of arbitrary objects, and the other is to generate top-down bias signal for selectively attending to a target object. Experimental results show that the proposed model performs well in successfully focusing on given target objects, as well as incrementally perceiving arbitrary objects in natural scenes.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Minho Lee,et al.  Top-Down Object Color Biased Attention Using Growing Fuzzy Topology ART , 2008, IDEAL.

[3]  T. Poggio,et al.  A model of V4 shape selectivity and invariance. , 2007, Journal of neurophysiology.

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

[5]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

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

[7]  Yoshifumi Nishio,et al.  Fuzzy Adaptive Resonance Theory Combining Overlapped Category in consideration of connections , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[8]  Koichiro Yamauchi,et al.  Fast incremental learning methods inspired by biological learning behavior , 2004, Artificial Life and Robotics.

[9]  B L McNaughton,et al.  Brain growth and the cognitive map. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[11]  Christof Koch,et al.  Modeling attention to salient proto-objects , 2006, Neural Networks.

[12]  Minho Lee,et al.  Saliency map model with adaptive masking based on independent component analysis , 2002, Neurocomputing.

[13]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[14]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[15]  Timothée Masquelier,et al.  Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity , 2007, PLoS Comput. Biol..

[16]  R. Desimone,et al.  Neural mechanisms of selective visual attention. , 1995, Annual review of neuroscience.

[17]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[18]  Shaun P. Vecera,et al.  Toward a Biased Competition Account of Object-Based Segregation and Attention , 2000 .

[19]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[20]  Bala Srinivasan,et al.  Dynamic self-organizing maps with controlled growth for knowledge discovery , 2000, IEEE Trans. Neural Networks Learn. Syst..

[21]  Stephen R. Marsland,et al.  A self-organising network that grows when required , 2002, Neural Networks.

[22]  Minho Lee,et al.  Stereo saliency map considering affective factors and selective motion analysis in a dynamic environment , 2008, Neural Networks.

[23]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[24]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[25]  Zhaoping Li,et al.  Computational Design and Nonlinear Dynamics of a Recurrent Network Model of the Primary Visual Cortex , 2001, Neural Computation.

[26]  FritzkeBernd.  Growing cell structuresa self-organizing network for unsupervised and supervised learning , 1994 .

[27]  Antonio Torralba,et al.  Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. , 2006, Psychological review.

[28]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[29]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[30]  Minho Lee,et al.  Biologically Motivated Incremental Object Perception Based on Selective Attention , 2007, Int. J. Pattern Recognit. Artif. Intell..