Learning viewpoint invariant perceptual representations from cluttered images

In order to perform object recognition, it is necessary to form perceptual representations that are sufficiently specific to distinguish between objects, but that are also sufficiently flexible to generalize across changes in location, rotation, and scale. A standard method for learning perceptual representations that are invariant to viewpoint is to form temporal associations across image sequences showing object transformations. However, this method requires that individual stimuli be presented in isolation and is therefore unlikely to succeed in real-world applications where multiple objects can co-occur in the visual input. This paper proposes a simple modification to the learning method that can overcome this limitation and results in more robust learning of invariant representations.

[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.  Ferrier lecture - Functional architecture of macaque monkey visual cortex , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  T. Wiesel,et al.  Functional architecture of macaque monkey visual cortex , 1977 .

[4]  Leslie G. Ungerleider.  Two cortical visual systems , 1982 .

[5]  Kunihiko Fukushima,et al.  Neocognitron: A hierarchical neural network capable of visual pattern recognition , 1988, Neural Networks.

[6]  Y. Miyashita.  Neuronal correlate of visual associative long-term memory in the primate temporal cortex , 1988, Nature.

[7]  M. H. Loew,et al.  Staged assimilation: a system for detecting invariant features in temporally coherent visual stimuli , 1989, International 1989 Joint Conference on Neural Networks.

[8]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[9]  H. Barlow.  Conditions for versatile learning, Helmholtz's unconscious inference, and the task of perception , 1990, Vision Research.

[10]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

[11]  J. Leo van Hemmen,et al.  Temporal association , 1991 .

[12]  M. Stryker.  Temporal associations , 1991, Nature.

[13]  M. Goodale,et al.  Separate visual pathways for perception and action , 1992, Trends in Neurosciences.

[14]  D I Perrett,et al.  Organization and functions of cells responsive to faces in the temporal cortex. , 1992, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[15]  Suzanna Becker,et al.  Learning to Categorize Objects Using Temporal Coherence , 1992, NIPS.

[16]  G. Wallis,et al.  Learning invariant responses to the natural transformations of objects , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[17]  M. Tovée,et al.  Translation invariance in the responses to faces of single neurons in the temporal visual cortical areas of the alert macaque. , 1994, Journal of neurophysiology.

[18]  Mark H. Johnson,et al.  Object Recognition and Sensitive Periods: A Computational Analysis of Visual Imprinting , 1994, Neural Computation.

[19]  Guy Wallis,et al.  Neural Mechanisms Underlying Processing in the Visual Areas of the Occipital and Temporal Lobes , 1994 .

[20]  Keiji Tanaka,et al.  Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. , 1994, Journal of neurophysiology.

[21]  James V. Stone,et al.  A learning rule for extracting spatio-temporal invariances , 1995 .

[22]  C. Gilbert.  Plasticity in visual perception and physiology , 1996, Current Opinion in Neurobiology.

[23]  Peter Földiák,et al.  Learning generalisation and localisation: Competition for stimulus type and receptive field , 1996, Neurocomputing.

[24]  Guy M. Wallis,et al.  Using Spatio-temporal Correlations to Learn Invariant Object Recognition , 1996, Neural Networks.

[25]  Martin Ebdon.  Towards a General Theory of Cerebral Neocortex , 1996 .

[26]  James V. Stone,et al.  A Canonical Microfunction for Learning Perceptual Invariances , 1996, Perception.

[27]  D. Peterson.  Forms of representation : an interdisciplinary theme for cognitive science , 1996 .

[28]  Tomaso Poggio,et al.  Role of learning in three-dimensional form perception , 1996, Nature.

[29]  Keiji Tanaka,et al.  Representation of Visual Features of Objects in the Inferotemporal Cortex , 1996, Neural Networks.

[30]  Terrence J. Sejnowski,et al.  Unsupervised Learning Of Invariant Representations Of Faces Through Temporal Association , 1996 .

[31]  A. Clark,et al.  Trading spaces: Computation, representation, and the limits of uninformed learning , 1997, Behavioral and Brain Sciences.

[32]  E. Rolls,et al.  INVARIANT FACE AND OBJECT RECOGNITION IN THE VISUAL SYSTEM , 1997, Progress in Neurobiology.

[33]  Tanaka Ungerleider,et al.  Vision and movement mechanisms in the cerebral cortex , 1997, Trends in Cognitive Sciences.

[34]  Guy Wallis,et al.  Temporal Order in Human Object Recognition Learning , 1998 .

[35]  V. Mountcastle.  Perceptual Neuroscience: The Cerebral Cortex , 1998 .

[36]  James V. Stone.  Object recognition using spatiotemporal signatures , 1998, Vision Research.

[37]  E. Rolls,et al.  View-invariant representations of familiar objects by neurons in the inferior temporal visual cortex. , 1998, Cerebral cortex.

[38]  T J Sejnowski,et al.  Learning viewpoint-invariant face representations from visual experience in an attractor network. , 1998, Network.

[39]  N. Logothetis.  Object vision and visual awareness. , 1998, Current opinion in neurobiology.

[40]  G. Wallis,et al.  Spatio-temporal influences at the neural level of object recognition. , 1998, Network.

[41]  G. Wallis.  Spatio-temporal influences at the neural level of object recognition , 1998 .

[42]  T. Poggio,et al.  Are Cortical Models Really Bound by the “Binding Problem”? , 1999, Neuron.

[43]  Suzanna Becker,et al.  Implicit Learning in 3D Object Recognition: The Importance of Temporal Context , 1999, Neural Computation.

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

[45]  Edmund T. Rolls,et al.  Position invariant recognition in the visual system with cluttered environments , 2000, Neural Networks.

[46]  Narendra Ahuja,et al.  Learning to recognize objects , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[47]  E. Rolls.  Functions of the Primate Temporal Lobe Cortical Visual Areas in Invariant Visual Object and Face Recognition , 2000, Neuron.

[48]  Edmund T. Rolls,et al.  A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition, and Information-Based Performance Measures , 2000, Neural Computation.

[49]  Konrad P. Körding,et al.  Neurons with Two Sites of Synaptic Integration Learn Invariant Representations , 2001, Neural Computation.

[50]  H. Bülthoff,et al.  Effects of temporal association on recognition memory , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[51]  G. Wallis.  The role of object motion in forging long-term representations of objects , 2002 .

[52]  Terrence J. Sejnowski,et al.  Slow Feature Analysis: Unsupervised Learning of Invariances , 2002, Neural Computation.

[53]  Michael W. Spratling,et al.  Preintegration Lateral Inhibition Enhances Unsupervised Learning , 2002, Neural Computation.

[54]  K. Clark.  CONDITIONS FOR VERSATILE LEARNING , HELMHOLTZ ’ S UNCONSCIOUS INFERENCE , AND THE TASK OF PERCEPTION , 2002 .

[55]  M. Tarr,et al.  Visual Object Recognition , 1996, ISTCS.

[56]  P. Lennie.  Receptive fields , 2003, Current Biology.

[57]  Michael W. Spratling,et al.  Neural coding strategies and mechanisms of competition , 2004, Cognitive Systems Research.

[58]  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.

[59]  P. Földiák,et al.  Forming sparse representations by local anti-Hebbian learning , 1990, Biological Cybernetics.