Promoting rotational-invariance in object recognition despite experience with only a single view

Different processes are assumed to underlie invariant object recognition across affine transformations, such as changes in size, and non-affine transformations, such as rotations in depth. From this perspective, promoting invariant object recognition across rotations in depth requires visual experience with the object from multiple viewpoints. One learning mechanism potentially contributing to invariant recognition is the error-driven learning of associations between relatively view-invariant visual properties and motor responses or object labels. This account uniquely predicts that experience with affine transformations of a single object view may also promote view-invariance, if view-invariant properties are also invariant across such affine transformations. We empirically confirmed this prediction in both people and pigeons, thereby suggesting that: (a) the hypothesized mechanism participates in view-invariance learning, (b) this mechanism is present across distantly-related vertebrates, and (c) the distinction between affine and non-affine transformations may not be fundamental for biological visual systems, as previously assumed.

[1]  I. Biederman,et al.  The Pigeon's Recognition of Drawings of Depth-Rotated Stimuli , 1996 .

[2]  Tomaso Poggio,et al.  Models of object recognition , 2000, Nature Neuroscience.

[3]  Tomaso Poggio,et al.  Fast Readout of Object Identity from Macaque Inferior Temporal Cortex , 2005, Science.

[4]  Edward A Wasserman,et al.  Missing the Forest for the Trees , 2010, Psychological science.

[5]  I Biederman,et al.  Seeing things from a different angle: the pigeon's recognition of single geons rotated in depth. , 2000, Journal of experimental psychology. Animal behavior processes.

[6]  Lloyd J. Frei,et al.  Recent advances in operant conditioning technology: A versatile and affordable computerized touchscreen system , 2004, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[7]  Edward A. Wasserman,et al.  View-invariance learning in object recognition by pigeons depends on error-driven associative learning processes , 2012, Vision Research.

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

[9]  Keiji Tanaka,et al.  Prior experience of rotation is not required for recognizing objects seen from different angles , 2005, Nature Neuroscience.

[10]  David D. Cox,et al.  'Breaking' position-invariant object recognition , 2005, Nature Neuroscience.

[11]  David D. Cox,et al.  What response properties do individual neurons need to underlie position and clutter "invariant" object recognition? , 2009, Journal of neurophysiology.

[12]  Edmund T. Rolls,et al.  Learning invariant object recognition in the visual system with continuous transformations , 2006, Biological Cybernetics.

[13]  Fabian A. Soto,et al.  Visual object categorization in birds and primates: Integrating behavioral, neurobiological, and computational evidence within a “general process” framework , 2011, Cognitive, Affective, & Behavioral Neuroscience.

[14]  I. Biederman,et al.  Inferior Temporal Neurons Show Greater Sensitivity to Nonaccidental than to Metric Shape Differences , 2001, Journal of Cognitive Neuroscience.

[15]  Charles F Stevens.  Preserving properties of object shape by computations in primary visual cortex. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[16]  Fabian A. Soto,et al.  A category-overshadowing effect in pigeons: support for the Common Elements Model of object categorization learning. , 2012, Journal of experimental psychology. Animal behavior processes.

[17]  I. Biederman,et al.  Shape Tuning in Macaque Inferior Temporal Cortex , 2003, The Journal of Neuroscience.

[18]  Isabel Gauthier,et al.  Three-dimensional object recognition is viewpoint dependent , 1998, Nature Neuroscience.

[19]  Tomaso Poggio,et al.  Trade-Off between Object Selectivity and Tolerance in Monkey Inferotemporal Cortex , 2007, The Journal of Neuroscience.

[20]  I. Biederman,et al.  Effects of varying stimulus size on object recognition in pigeons. , 2006, Journal of experimental psychology. Animal behavior processes.

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

[22]  Fabian A. Soto,et al.  Error-driven learning in visual categorization and object recognition: a common-elements model. , 2010, Psychological review.

[23]  A Friedman,et al.  The effect of distinctive parts on recognition of depth-rotated objects by pigeons (Columba livia) and humans. , 2001, Journal of experimental psychology. General.

[24]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

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

[26]  Edward A. Wasserman,et al.  Pigeons and humans are more sensitive to nonaccidental than to metric changes in visual objects , 2008, Behavioural Processes.

[27]  D H Brainard,et al.  The Psychophysics Toolbox. , 1997, Spatial vision.

[28]  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.

[29]  David J. Field,et al.  Wavelets, vision and the statistics of natural scenes , 1999, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[30]  Dwight J. Kravitz,et al.  How position dependent is visual object recognition? , 2008, Trends in Cognitive Sciences.

[31]  R. Vogels,et al.  Spatial sensitivity of macaque inferior temporal neurons , 2000, The Journal of comparative neurology.

[32]  Fabian A. Soto,et al.  Mechanisms of object recognition: what we have learned from pigeons , 2014, Front. Neural Circuits.

[33]  P. Schyns,et al.  Nonaccidental Properties Underlie Shape Recognition in Mammalian and Nonmammalian Vision , 2007, Current Biology.

[34]  Robbe L. T. Goris,et al.  Invariance in Visual Object Recognition Requires Training: A Computational Argument , 2009, Frontiers in neuroscience.

[35]  I. Biederman,et al.  Recognition-by-components: A bird's eye view. , 2012 .

[36]  James J. DiCarlo,et al.  Unsupervised Natural Experience Rapidly Alters Invariant Object Representation in Visual Cortex , 2008, Science.

[37]  A. N. Bowers,et al.  Visual circuits of the avian telencephalon: evolutionary implications , 1999, Behavioural Brain Research.

[38]  Keiji Tanaka,et al.  View‐invariant object recognition ability develops after discrimination, not mere exposure, at several viewing angles , 2010, The European journal of neuroscience.