|
|
Reading material for CN730
Computational models of high-level vision
|
>> SLIDES available here
The "must-read":
- On the role of feedforward vs. recurrent processing in the visual cortex:
- Lamme et al. The distinct modes of vision offered by feedforward and recurrent processing. Trends Neurosci (2000) vol. 23 (11) pp. 571-9 [PDF]
This paper gives a good general description of the feedforward/feedback framework that I am going to describe during the lecture.
- Feedforward hierachical models of object recognition in the visual cortex:
- T.
Serre, M. Kouh, C. Cadieu, U. Knoblich, G. Kreiman
and T. Poggio. A theory of object recognition:
computations and circuits in the feedforward path
of the ventral stream in primate visual cortex,
CBCL Paper #259/AI Memo #2005-036, Massachusetts
Institute of Technology, Cambridge, MA, December,
2005 [PDF]
This is essentially a complete overview of the computational framework that I am going to present. This memo is very long and detailed and the point is not to read everything. I would recommend to read the introduction for a general overview and to briefly look at a few sections of interest.
- T.
Serre, A. Oliva and T. Poggio. A feedforward
architecture accounts for rapid categorization.
Proceedings of the National Academy of Science,
104(15), pp. 6424-6429, April 2007 [ OPEN ACCESS]
An illutration of what feedforward hierarchical architectures can and cannot do.
- Beyond feedforward processing:
- Epshtein et al. Image interpretation by a single bottom-up top-down cycle. Proceedings of the National Academy of Sciences (2008). [PDF]
An illutration of how feedback/re-entrant processing could contribute beyond an initial feedforward sweep.
|
Additional readings:
- Hierarchy/subunit organization
- Hubel, D. H., and T. N. Wiesel: Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. J. Physiol. 160: 106-154 (1962) [PDF]
Mostly for historical reasons. You should read it if you have not.
- Chen et al. Excitatory and suppressive receptive field subunits in awake monkey primary visual cortex (V1). Proc Natl Acad Sci USA (2007) vol. 104 (48) pp. 19120-5. [PDF]
A recent study providing evidence for a subunit organization a la Hubel & Wiesel.
- Feedforward processing / rapid animal categorization
- Thorpe et al. Speed of processing in the human visual system. Nature (1996) vol. 381 (6582) pp. 520-2 [PDF]
A classical paper that you should read if you have not.
- Performance of feedforward hierarchical models in computer vision applications:
- T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber and T. Poggio. Object recognition with cortex-like mechanisms. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 29 (3), pp. 411-426 , 2007 [PDF]
- H. Jhuang,
T. Serre, L. Wolf and T. Poggio. A biologically
inspired system for action recognition. In: Proceedings
of the Eleventh IEEE International Conference
on Computer Vision (ICCV), 2007 [PDF]
The two papers above illustrate how neuroscience may provide some inspiration for computer vision applications.
- Bayesian models of cortical feedback
- Lee et al. Hierarchical Bayesian inference in the visual cortex. J Opt Soc Am A Opt Image Sci Vis (2003) vol. 20 (7) pp. 1434-48 [PDF]
- Hegdé et al. Reappraising the functional implications of the primate visual anatomical hierarchy. The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry (2007) vol. 13 (5) pp. 416-21[PDF]
|
|
|
|
|