One-shot viewpoint invariance in matching novel objects

Humans often evidence little difficulty at recognizing objects from arbitrary orientations in depth. According to one class of theories, this competence is based on generalization from templates specified by metric properties (MPs), that were learned for the various orientations. An alternative class of theories assumes that non-accidental properties (NAPs) might be exploited so that even novel objects can be recognized under depth rotation. After scaling MP and NAP differences so that they were equally detectable when the objects were at the same orientation in depth, the present investigation assessed the effects of rotation on same-different judgments for matching novel objects. Judgments of a sequential pair of images of novel objects, when rendered from different viewpoints, revealed relatively low costs when the objects differed in a NAP of a single part, i.e. a geon. However, rotation dramatically reduced the detectability of MP differences to a level well below that expected by chance. NAPs offer a striking advantage over MPs for object classification and are therefore more likely to play a central role in the representation of objects.

[1]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[2]  Kavitha Srinivas.  Perceptual specificity in nonverbal priming. , 1993 .

[3]  G. Humphrey,et al.  Recognizing novel views of three-dimensional objects. , 1992, Canadian journal of psychology.

[4]  I. Biederman,et al.  Evidence for Complete Translational and Reflectional Invariance in Visual Object Priming , 1991, Perception.

[5]  J. Hummel,et al.  The role of attention in priming for left-right reflections of object images: evidence for a dual representation of object shape. , 1998, Journal of experimental psychology. Human perception and performance.

[6]  M. J. Tarr,et al.  COMMENT ON: IS HUMAN OBJECT RECOGNITION BETTER DESCRIBED BY GEON STRUCTURAL DESCRIPTIONS OR BY MULTIPLE VIEWS ? BY BARTRAM D.J. , 1995 .

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

[8]  D. Jacobs.  Space Efficient 3D Model Indexing , 1992 .

[9]  T. Poggio,et al.  Symmetric 3D objects are an easy case for 2D object recognition. , 1994, Spatial vision.

[10]  N. Logothetis,et al.  View-dependent object recognition by monkeys , 1994, Current Biology.

[11]  M. Tarr,et al.  To What Extent Do Unique Parts Influence Recognition Across Changes in Viewpoint? , 1995 .

[12]  S. Edelman,et al.  Orientation dependence in the recognition of familiar and novel views of three-dimensional objects , 1992, Vision Research.

[13]  Zenon W. Pylyshyn,et al.  Computational processes in human vision , 1988 .

[14]  I. Rock,et al.  A case of viewer-centered object perception , 1987, Cognitive Psychology.

[15]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[16]  M. Kubovy,et al.  Mental Rotation, Mental Representation, and Flat Slopes , 1993, Cognitive Psychology.

[17]  I Biederman,et al.  Metric invariance in object recognition: a review and further evidence. , 1992, Canadian journal of psychology.

[18]  J. Hochberg,et al.  The effect of landmark features on mental rotation times , 1977, Memory & cognition.

[19]  I. Biederman,et al.  Viewpoint-dependent mechanisms in visual object recognition: Reply to Tarr and Bülthoff (1995). , 1995 .

[20]  H. Intraub.  Conceptual masking: the effects of subsequent visual events on memory for pictures. , 1984, Journal of experimental psychology. Learning, memory, and cognition.

[21]  Jean Bullier,et al.  The Timing of Information Transfer in the Visual System , 1997 .

[22]  I. Biederman,et al.  Subordinate-level object classification reexamined , 1999, Psychological research.

[23]  M. Tarr,et al.  Testing conditions for viewpoint invariance in object recognition. , 1997, Journal of experimental psychology. Human perception and performance.

[24]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[25]  M J Tarr,et al.  Is human object recognition better described by geon structural descriptions or by multiple views? Comment on Biederman and Gerhardstein (1993). , 1995, Journal of experimental psychology. Human perception and performance.

[26]  I. Biederman,et al.  Size invariance in visual object priming , 1992 .

[27]  I. Biederman,et al.  Recognizing depth-rotated objects: Evidence and conditions for three-dimensional viewpoint invariance. , 1993 .

[28]  I. Biederman,et al.  Priming contour-deleted images: Evidence for intermediate representations in visual object recognition , 1991, Cognitive Psychology.

[29]  Howard E. Egeth,et al.  Multidimensional stimulus identification , 1969 .

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

[31]  H. Egeth.  Parallel versus serial processes in multidimensional stimulus discrimination , 1966 .