[BibTeX] [RIS]
Learning the 2-D Topology of Images
Type of publication: Inproceedings
Citation: NIPS2007-925
Booktitle: Advances in Neural Information Processing Systems 20 (NIPS'07)
Year: 2008
Pages: 841--848
Publisher: MIT Press
Address: Cambridge, MA
Crossref: NIPS20:
Advances in Neural Information Processing Systems 20 (NIPS'07), Platt, John, Koller, D., Singer, Yoram and Roweis, S. (eds), in: Advances in Neural Information Processing Systems 20 (NIPS'07), MIT Press, -1
Abstract: We study the following question: is the two-dimensional structure of images a very strong prior or is it something that can be learned with a few examples of natural images? If someone gave us a learning task involving images for which the two-dimensional topology of pixels was not known, could we discover it automatically and exploit it? For example suppose that the pixels had been permuted in a fixed but unknown way, could we recover the relative two-dimensional location of pixels on images? The surprising result presented here is that not only the answer is yes but that about as few as a thousand images are enough to approximately recover the relative locations of about a thousand pixels. This is achieved using a manifold learning algorithm applied to pixels associated with a measure of distributional similarity between pixel intensities. We compare different topologyextraction approaches and show how having the two-dimensional topology can be exploited.
Keywords:
Authors Le Roux, Nicolas
Bengio, Yoshua
Lamblin, Pascal
Joliveau, Marc
Kégl, Balázs
Editors Platt, John
Koller, D.
Singer, Yoram
Roweis, S.
Added by: [ADM]
Total mark: 0
Attachments
  • nips2007_submission.pdf
Notes
    Topics