Similarity, Connectionism, and the Problem of Representation in Vision
Neural ComputationPublished 1 May 1997
Shimon Edelman, Sharon Duvdevani-Bar
Citations40
SJR quartileQ1
SJR score0.83
SNIP1.45
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The computational requirements of representation that preserves similarity ranks are discussed and the relative straightforwardness of its connectionist implementation is pointed out.
Abstract
A representational scheme under which the ranking between represented similarities is isomorphic to the ranking between the corresponding shape similarities can support perfectly correct shape classification because it preserves the clustering of shapes according to the natural kinds prevailing in the external world. This article discusses the computational requirements of representation that preserves similarity ranks and points out the relative straightforwardness of its connectionist implementation.
Keywords
PsychologyComputer ScienceNeuroscience
Machine LearningSupport-vector networks
40,463 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Machine LearningSupport-Vector Networks
33,035 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Psychological ReviewFeatures of similarity.
7,287 Citations1977Amos Tversky
The metric and dimensional assumptions that underlie the geometric representation of similarity are questioned on both theoretical and empirical grounds and a set of qualitative assumptions are shown to imply the contrast model, which expresses the similarity between objects as a linear combination of the measures of their common and distinctive features.
International Journal of Computer VisionColor indexing
5,592 Citations1991Michael J. Swain, Dana H. Ballard
It is demonstrated that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models and that they can differentiate among a large number of objects.
Cognitive PsychologyBasic objects in natural categories
5,526 Citations1976Eleanor Rosch, Carolyn Β. Mervis +3 more
ScienceToward a Universal Law of Generalization for Psychological Science
2,475 Citations1987Roger N. Shepard
A psychological space is established for any set of stimuli by determining metric distances between the stimuli such that the probability that a response learned to any stimulus will generalize to any other is an invariant monotonic function of the distance between them.
The organization of learning
2,463 Citations1990C. R. Gallistel
Journal of NeurophysiologyVisual properties of neurons in inferotemporal cortex of the Macaque.
1,501 Citations1972Charles G. Gross, Carlos Eduardo Rocha‐Miranda +1 more
There are several lines of evidence suggesting that a possible site for further processing of visual information and perhaps even for storage of such information might, in the monkey, be inferotemporal cortexthe cortex on the inferior convexity of the temporal lobe.
Lecture notes in mathematicsLectures on n-Dimensional Quasiconformal Mappings
1,210 Citations1971Jussi Väısälä
Current BiologyShape representation in the inferior temporal cortex of monkeys
980 Citations1995Nikos K. Logothetis, J Pauls +1 more
The results suggest that IT neurons can develop a complex receptive field organization as a consequence of extensive training in the discrimination and recognition of objects, and support the idea that a population of neurons tuned to a different object aspect, and each showing a certain degree of invariance to image transformations--may encode at least some types of complex three-dimensional objects.
NatureA network that learns to recognize three-dimensional objects
936 Citations1990Tomaso Poggio, Shimon Edelman
A scheme is developed, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view, and a network equivalent to this scheme will 'recognize' the object on which it was trained from any viewpoint.
Journal of NeurophysiologyNeuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex
832 Citations1994Eiry Kobatake, Keiji Tanaka
It is suggested that local neuronal networks in V4 and posterior IT play an essential role in the formation of selective responses to complex object features.
IEEE ExpertInduction: Processes of Inference, Learning, and Discovery
824 Citations1987John H. Holland, Keith J. Holyoak +3 more
Induction is the first major effort to bring the ideas of several disciplines to bear on a subject that has been a topic of investigation since the time of Socrates and is included in the Computational Models of Cognition and Perception Series.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecognition by linear combinations of models
817 Citations1991Shimon Ullman, Ronen Basri
An approach to visual object recognition in which a 3D object is represented by the linear combination of 2D images of the object is proposed and it is shown that for objects with sharp edges as well as with smooth bounding contours, the set of possible images of a given object is embedded in a linear space spanned by a small number of views.
ScienceMultidimensional Scaling, Tree-Fitting, and Clustering
754 Citations1980Roger N. Shepard
Applications to perceptual and semantic data illustrate how complementary aspects of the underlying psychological structure are revealed by different types of representations, including multidimensional spatial configurations and nondimensional tree-structures or clusterings.
Cognitive PsychologySecond-order isomorphism of internal representations: Shapes of states
650 Citations1970Roger N. Shepard, Susan F. Chipman
NatureColumns for visual features of objects in monkey inferotemporal cortex
637 Citations1992Ichiro Fujita, Keiji Tanaka +2 more
The anterior inferotemporal area of the monkey cortex, the final station of the visual cortical stream crucial for object recognition, consists of columns, each containing cells responsive to similar visual features of objects.
Israel Journal of MathematicsOn lipschitz embedding of finite metric spaces in Hilbert space
545 Citations1985Jean Bourgain
Translations of mathematical monographsSpace Mappings with Bounded Distortion
528 Citations1989Yu. G. Reshetnyak
ScienceNeuronal Mechanisms of Object Recognition
522 Citations1993Keiji Tanaka
Recent experimental findings about the representation of object images in the inferotemporal cortex, a brain structure that is thought to be essential for object vision, are summarized and discussed in relation to the computational frames proposed for object recognition.
Journal of Experimental Psychology Learning Memory and CognitionExemplar-based accounts of relations between classification, recognition, and typicality.
509 Citations1988Robert M. Nosofsky
Previously published sets of classification and old-new recognition memory data are reanalyzed within the framework of an exemplar-based generalization model and the summed-similarity decision rule is shown to be consistent with a wide variety of recognition memoryData obtained in classification learning situations and may provide a unified approach to understanding relations between categorization and recognition.
CognitionThe role of similarity in categorization: providing a groundwork
476 Citations1994Robert L. Goldstone
A reassessment of evidence indicates that similarity can be sufficiently constrained and sophisticated to provide at least a partial account of many categories.
Multidimensional Similarity Structure Analysis
415 Citations1987Ingwer Borg, J. Lingoes
This work focuses on the construction of Ordinal SSA Representations, a type of model for SSA that combines Ordinal and Ratio data structures, and three applications of SSA, which aim to address the problem of degeneracies.
The Roots of Reference
399 Citations1974W. V. Quine
Neural ComputationSEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition
344 Citations1997Bartlett W. Mel
It is concluded that in the light of the vast hardware resources available in the ventral stream of the primate visual system relative to those exercised here, the appealingly simple feature-space conjecture remains worthy of serious consideration as a neurobiological model.
Proceedings of the National Academy of SciencesShifter circuits: a computational strategy for dynamic aspects of visual processing.
284 Citations1987Charles H. Anderson, David C. Van Essen
The shifter hypothesis is consistent with available anatomical and physiological evidence on the organization of the primate visual pathway, and it offers a sensible explanation for a variety of otherwise puzzling facts, such as the plethora of cells in the geniculorecipient layers of V1.
The American Journal of PsychologyRepresentations, Targets, and Attitudes
238 Citations1999J. D. Trout, Robert Cummins
The geometry of graphs and some of its algorithmic applications
189 Citations2002Nathan Linial, Eran London +1 more
Efficient algorithms for embedding graphs low-dimensionally with a small distortion, and a new deterministic polynomial-time algorithm that finds a (nearly tight) cut meeting this bound.
Minds and MachinesRepresentation, similarity, and the chorus of prototypes
164 Citations1995Shimon Edelman
The present preliminary study appears to indicate that this concept of representation is computationally viable, and is compatible with psychological and neurobiological data.
Vision ResearchStimulus-specific effects in face recognition over changes in viewpoint
157 Citations1998Alice J. O’Toole, Shimon Edelman +1 more
The results suggest that the stimulus information captured in the model measures may underlie distinct and dissociable aspects of the recognizability of individual faces across viewpoint change.
Trends in Cognitive SciencesComputational theories of object recognition
89 Citations1997Shimon Edelman
This paper examines four current theoretical approaches to the representation and recognition of visual objects: structural descriptions, geometric constraints, multidimensional feature spaces and shape-space approximation.
Current Opinion in NeurobiologyInferotemporal cortex and higher visual functions
87 Citations1992Keiji Tanaka
A columnar organization has been revealed, and a short-term change of responsiveness has been proposed as a neural correlate of working memory.
Learning & MemoryNeuronal tuning and associative mechanisms in form representation.
84 Citations1994Kuniyoshi L. Sakai, Yuji Naya +1 more
A model of the cognitive memory system that unifies perception and imagery is presented, which shows that long-term memory of objects is acquired and organized by at least at least two neuronal mechanisms in the temporal association area.
The Psychology of learning and motivation/The psychology of learning and motivationLearning as Extraction of Low-Dimensional Representations
66 Citations1997Shimon Edelman, Nathan Intrator
This chapter discusses that the effectiveness of living representational systems suggest that there must be something special about such systems that allows them to harbor representations of the world, and suggests that the possibility of effective representation stems from theLow-dimensional nature of the real-world classification tasks: an intelligent system would do well merely by reflecting the low-dimensional distal space internally.
Vision ResearchRepresentation of object similarity in human vision: psychophysics and a computational model
65 Citations1998Florin Cutzu, Shimon Edelman
Results from perceptual judgment, delayed matching to sample and long-term memory recall experiments, and computational model that accompanies the psychophysical data indicate that the human visual system can support metrically veridical representations of similarities among 3D objects.
Proceedings of the National Academy of SciencesFaithful representation of similarities among three-dimensional shapes in human vision.
53 Citations1996Florin Cutzu, Shimon Edelman
This work investigated the ability of the human visual system to derive representations from the sensory input-a highly nontrivial task, given the million or so dimensions of the visual signal at its entry point to the cortex.
Neural ComputationRepresentation of Similarity in Three-Dimensional Object Discrimination
51 Citations1995Shimon Edelman
The results of four tests support the notion that discrimination among 3D objects may rely on a low-dimensional feature space representation, and suggest that this space may be spanned by explicitly encoded class prototypes.
Neural ComputationCombining Exploratory Projection Pursuit and Projection Pursuit Regression with Application to Neural Networks
39 Citations1993Nathan Intrator
A novel classification and regression method that combines exploratory projection pursuit (unsupervised training) with projection pursuit regression ( supervised training), to yield a new family of cost/complexity penalty terms.
Lecture notes in mathematicsThe global homeomorphism theorem for space quasiconformal mappings, its development and related open problems
32 Citations1992Владимир Антонович Зорич
A similarity-based method for the generalization of face recognition over pose and expression
28 Citations2002Sharon Duvdevani-Bar, Shimon Edelman +2 more
A working computational model of generalization from a single view is constructed and tested on a homogeneous database of face images obtained under tightly controlled viewing conditions, which effectively constructs a view space for novel faces by interpolating view spaces of familiar ones.
CogPrints (Cogprints)Representation of Similarity in 3D Object Discrimination
27 Citations1995Shimon Edelman
Annual Review of PsychologyRepresentations and Models in Psychology
21 Citations1994P. Suppes, Pavel Mautner +1 more
Neural Information Processing SystemsConnectionist Implementation of a Theory of Generalization
21 Citations1990Roger N. Shepard, Sheila J. Kannappan
A natural connectionist implementation of the generalization theory is described, and how implications of the theory for generalization, discrimination, and classification learning can be explored by connectionist simulation is illustrated.
Lecture notes in biomathematicsThe Past, Present and Future of Feature Detectors
7 Citations1982H. B. Barlow
The past history of feature detectors is looked at, a bit about my present work, and a brief guess at the future is taken.