A Competitive-Layer Model for Feature Binding and Sensory Segmentation

We present a recurrent neural network for feature binding and sensory segmentation: the competitive-layer model (CLM). The CLM uses topo-graphically structured competitive and cooperative interactions in a layered network to partition a set of input features into salient groups. The dynamics is formulated within a standard additive recurrent network with linear threshold neurons. Contextual relations among features are coded by pairwise compatibilities, which define an energy function to be minimized by the neural dynamics. Due to the usage of dynamical winner-take-all circuits, the model gains more flexible response properties than spin models of segmentation by exploiting amplitude information in the grouping process. We prove analytic results on the convergence and stable attractors of the CLM, which generalize earlier results on winner-take-all networks, and incorporate deterministic annealing for robustness against local minima. The piecewise linear dynamics of the CLM allows a linear eigensubspace analysis, which we use to analyze the dynamics of binding in conjunction with annealing. For the example of contour detection, we show how the CLM can integrate figure-ground segmentation and grouping into a unified model.

[1]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[2]  D. Hubel,et al.  Laminar and columnar distribution of geniculo‐cortical fibers in the macaque monkey , 1972, The Journal of comparative neurology.

[3]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  J. Lund,et al.  Intrinsic laminar lattice connections in primate visual cortex , 1983, The Journal of comparative neurology.

[5]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  G. Blasdel,et al.  Physiological organization of layer 4 in macaque striate cortex , 1984, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[7]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  J. Lund.  Local circuit neurons of macaque monkey striate cortex: I. Neurons of laminae 4C and 5A , 1987, The Journal of comparative neurology.

[9]  Carsten Peterson,et al.  A New Method for Mapping Optimization Problems Onto Neural Networks , 1989, Int. J. Neural Syst..

[10]  Behrooz Kamgar-Parsi,et al.  On problem solving with Hopfield neural networks , 1990, International 1989 Joint Conference on Neural Networks.

[11]  Steven W. Zucker,et al.  Trace Inference, Curvature Consistency, and Curve Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Steven W. Zucker,et al.  Two Stages of Curve Detection Suggest Two Styles of Visual Computation , 1989, Neural Computation.

[13]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[14]  Joachim M. Buhmann,et al.  Computing with Arrays of Coupled Oscillators , 1990 .

[15]  Pierre Baldi,et al.  Computing with Arrays of Coupled Oscillators: An Application to Preattentive Texture Discrimination , 1990, Neural Computation.

[16]  Donald Geman,et al.  Boundary Detection by Constrained Optimization , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Helge Ritter,et al.  A Spatial Approach to Feature Linking , 1990 .

[18]  Sompolinsky,et al.  Cooperative dynamics in visual processing. , 1991, Physical review. A, Atomic, molecular, and optical physics.

[19]  J. Lund,et al.  Local circuit neurons of macaque monkey striate cortex: III. Neurons of laminae 4B, 4A, and 3B , 1997, The Journal of comparative neurology.

[20]  C. Gilbert.  Horizontal integration and cortical dynamics , 1992, Neuron.

[21]  David J. Field,et al.  Contour integration by the human visual system: Evidence for a local “association field” , 1993, Vision Research.

[22]  I Kovács,et al.  A closed curve is much more than an incomplete one: effect of closure in figure-ground segmentation. , 1993, Proceedings of the National Academy of Sciences of the United States of America.

[23]  Geoffrey C. Fox,et al.  Constrained Clustering as an Optimization Method , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Radu Horaud,et al.  Figure-Ground Discrimination: A Combinatorial Optimization Approach , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Leif H. Finkel,et al.  Dual Mechanisms for Neural Binding and Segmentation , 1993, NIPS.

[26]  Marcello Pelillo,et al.  On the dynamics of relaxation labeling processes , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[27]  I. Ohzawa,et al.  Length and width tuning of neurons in the cat's primary visual cortex. , 1994, Journal of neurophysiology.

[28]  U. Polat,et al.  The architecture of perceptual spatial interactions , 1994, Vision Research.

[29]  D. Sagi,et al.  The Architecture of Perceptual Spatial , 1994 .

[30]  R. Eckhorn,et al.  Oscillatory and non-oscillatory synchronizations in the visual cortex and their possible roles in associations of visual features. , 1994, Progress in brain research.

[31]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[32]  J. B. Levitt,et al.  Independence and merger of thalamocortical channels within macaque monkey primary visual cortex: Anatomy of interlaminar projections , 1994, Visual Neuroscience.

[33]  D. Fitzpatrick,et al.  Patterns of excitation and inhibition evoked by horizontal connections in visual cortex share a common relationship to orientation columns , 1995, Neuron.

[34]  H. Sompolinsky,et al.  Theory of orientation tuning in visual cortex. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[35]  J. Besag,et al.  Bayesian Computation and Stochastic Systems , 1995 .

[36]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[37]  C. von der Malsburg.  Binding in models of perception and brain function. , 1995, Current opinion in neurobiology.

[38]  C. Koch,et al.  Recurrent excitation in neocortical circuits , 1995, Science.

[39]  W Singer,et al.  Visual feature integration and the temporal correlation hypothesis. , 1995, Annual review of neuroscience.

[40]  C. Malsburg.  Binding in models of perception and brain function , 1995, Current Opinion in Neurobiology.

[41]  C. Gilbert,et al.  Improvement in visual sensitivity by changes in local context: Parallel studies in human observers and in V1 of alert monkeys , 1995, Neuron.

[42]  Steven W. Zucker,et al.  Computing Contour Closure , 1996, ECCV.

[43]  John Sum,et al.  Note on the Maxnet Dynamics , 1996, Neural Computation.

[44]  Alexander Dimitrov,et al.  Visual Cortex Circuitry and Orientation Tuning , 1996, NIPS.

[45]  Leif H. Finkel,et al.  Salient Contour Extraction by Temporal Binding in a Cortically-based Network , 1996, NIPS.

[46]  Eytan Domany,et al.  Data Clustering Using a Model Granular Magnet , 1997, Neural Computation.

[47]  Jianfeng Feng,et al.  Lyapunov Functions for Neural Nets with Nondifferentiable Input-Output Characteristics , 1997, Neural Computation.

[48]  J. Buhmann,et al.  Pairwise Data Clustering , 1997 .

[49]  Joachim M. Buhmann,et al.  Pairwise Data Clustering by Deterministic Annealing , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[50]  DeLiang Wang,et al.  Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.

[51]  Guy J. Brown,et al.  Modelling the perceptual segregation of double vowels with a network of neural oscillators , 1997, Neural Networks.

[52]  Heiko Wersing,et al.  A Layered Recurrent Neural Network for Feature Grouping , 1997, ICANN.

[53]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[54]  H. Ritter,et al.  Perceptual Grouping in a Neural Model: Reproducing Human Texture Perception , 1998 .

[55]  A Fast and Robust Cluster Update Algorithm for Image Segmentation in Spin-Lattice Models Without AnnealingVisual Latencies Revisited , 1998, Neural Computation.

[56]  Peter Dayan,et al.  Computational Differences between Asymmetrical and Symmetrical Networks , 1998, NIPS.

[57]  L. Finkel,et al.  Extraction of perceptually salient contours by striate cortical networks , 1998, Vision Research.

[58]  Richard H. R. Hahnloser,et al.  On the piecewise analysis of networks of linear threshold neurons , 1998, Neural Networks.

[59]  E. Callaway,et al.  Functional Streams and Local Connections of Layer 4C Neurons in Primary Visual Cortex of the Macaque Monkey , 1998, The Journal of Neuroscience.

[60]  Florentin Wörgötter,et al.  A Fast And Robust Cluster Update Algorithm For Image Segmentation In Spin-Lattice Models Without Annealing - Visual Latencies Revisited , 1998, Neural Comput..

[61]  Zhaoping Li,et al.  A Neural Model of Contour Integration in the Primary Visual Cortex , 1998, Neural Computation.

[62]  Heiko Wersing,et al.  Feature binding and relaxation labeling with the competitive layer model , 1999, ESANN.

[63]  Kaleem Siddiqi,et al.  Contour Fragment Grouping and Shared, Simple Occluders , 1999, Comput. Vis. Image Underst..

[64]  Heiko Wersing,et al.  Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions , 2001, Neural Computation.

[65]  Jochen J. Steil.  Local stability of recurrent networks with time-varying weights and inputs , 2002, Neurocomputing.

[66]  Barbara Hammer,et al.  Recurrent networks for structured data – A unifying approach and its properties , 2002, Cognitive Systems Research.

[67]  Xiaohui Xie,et al.  Selectively Grouping Neurons in Recurrent Networks of Lateral Inhibition , 2002, Neural Computation.

[68]  Akio Utsugi,et al.  Independent components of natural images under variable compression rate , 2002, Neurocomputing.