Hierarchical models of object recognition in cortex

@article{Riesenhuber1999HierarchicalMO,
  title={Hierarchical models of object recognition in cortex},
  author={Maximilian Riesenhuber and Tomaso A. Poggio},
  journal={Nature Neuroscience},
  year={1999},
  volume={2},
  pages={1019-1025}
}
Visual processing in cortex is classically modeled as a hierarchy of increasingly sophisticated representations, naturally extending the model of simple to complex cells of Hubel and Wiesel. Surprisingly, little quantitative modeling has been done to explore the biological feasibility of this class of models to explain aspects of higher-level visual processing such as object recognition. We describe a new hierarchical model consistent with physiological data from inferotemporal cortex that… 
How a Part of the Brain Might or Might Not Work: A New Hierarchical Model of Object Recognition
TLDR
Experimental evidence is found that training builds a viewpointand class-specific representation that supplements a pre-existing representation with lower shape discriminability but greater viewpoint invariance, and it is shown how HMAX can be extended in a straightforward fashion to perform object categorization and to support arbitrary class hierarchies.
An inferior temporal cortex model for object recognition and classification
TLDR
It is shown by simulation that the proposed neural-network model of the ventral visual stream is capable of classifying artificial three-dimensional objects according to their structural similarity and of achieving view-invariant recognition of the objects.
Attention can improve a simple model for object recognition
TLDR
This work explores and compares the H MAX model with a simpler model for object recognition emulating simple cells in the primary visual cortex, V1, and shows a better performance than the HMAX model for translation and scale invariance experiments when an attentional mechanism is employed in realistic conditions.
Object-specific Features , Biological Vision and Real World Object Recognition
Previous Work: We propose an extension of the HMAX model of object recognition in cortex [3] that characterizes the ventral visual pathway in cortex, extending from primary visual cortex, V1, to
Models of the Visual Cortex for Object Representation: Learning and Wired Approaches
TLDR
The status of computational modeling for object recognition is reviewed and what can be the next challenges to solve is proposed.
Neural representation for object recognition in inferotemporal cortex
We suggest that population representation of objects in inferotemporal cortex lie on a continuum between a purely structural, parts-based description and a purely holistic description. The intrinsic
The Role of Prototype Learning in Hierarchical Models of Vision.
TLDR
This work broadens the understanding of HMAX and related hierarchical models as tools for theoretical neuroscience, while simultaneously increasing the utility of such models as applied computer vision systems.
Human visual object categorization can be described by models with low memory capacity
TLDR
It is suggested that a sparse, abstracted representation of category properties may underlie categorization performance and could also be extracted directly from two-dimensional images via a biologically plausible early-vision model, rather than relying on experimenter-imposed features.
Investigating Shape Representation in Intermediate Areas of Visual Cortex with the Standard Model of Object Recognition
The Problem: The ventral pathway of the primate cortex is thought to mediate object recognition. Neurons within this pathway are classified in a hierarchical structure and exhibit selectivity to
Computational Models of Visual Object Recognition
TLDR
Some of the initial steps toward a theoretical understanding of the computational principles behind transformation-invariant visual recognition in the primate cortex are summarized.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 51 REFERENCES
Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects.
We describe a model of visual processing in which feedback connections from a higher- to a lower- order visual cortical area carry predictions of lower-level neural activities, whereas the
Shape representation in the inferior temporal cortex of monkeys
TLDR
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.
INVARIANT FACE AND OBJECT RECOGNITION IN THE VISUAL SYSTEM
Neurophysiological evidence is described, showing that some neurons in the macaque temporal cortical visual areas have responses that are invariant with respect to the position, size and view of
Neural Models for Part-Whole Hierarchies
We present a connectionist method for representing images that explicitly addresses their hierarchical nature. It blends data from neuroscience about whole-object viewpoint sensitive cells in
A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information
TLDR
A biologically plausible model of an attentional mechanism for forming position- and scale-invariant representations of objects in the visual world that respects key neurophysiological, neuroanatomical, and psychophysical data relating to attention, and it makes a variety of experimentally testable predictions.
View-invariant representations of familiar objects by neurons in the inferior temporal visual cortex.
TLDR
A population of single neurons in the temporal visual cortex that have view-invariant representations of familiar objects are described, and the coding scheme was shown to be sparse distributed, with relatively independent information being provided by the different neurons.
A selection model for motion processing in area MT of primates
  • SJ Nowlan, T. Sejnowski
  • Psychology, Medicine
    The Journal of neuroscience : the official journal of the Society for Neuroscience
  • 1995
A computational model for motion processing in area MT is presented that is based on the observed response properties of cortical neurons and is consistent with the visual perception of partially
A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition, and Information-Based Performance Measures
TLDR
It is shown that the sigmoid activation functions used in VisNet2, which allow the sparseness of the representation to be controlled, allow good performance when using sparse distributed representations and that this is related to temporal difference learning.
Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex.
TLDR
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.
Object vision and visual awareness.
  • N. Logothetis
  • Psychology, Medicine
    Current opinion in neurobiology
  • 1998
TLDR
Physiological and neuropsychological investigations suggest that awareness of a visual stimulus probably reflects the interconnectivity and the type of cells involved in the representation of this stimulus, rather than the activity of specific circumscribed visual areas or processing streams.
...
1
2
3
4
5
...