CaltechAUTHORS
  A Caltech Library Service

Unsupervised Category Discovery in Images Using Sparse Neural Coding

Waydo, Stephen and Koch, Christof (2007) Unsupervised Category Discovery in Images Using Sparse Neural Coding. In: Proceedings of the British Machine Vision Conference 2007. BMVA Press , Durham, UK, Art. No. 102. ISBN 1901725340. http://resolver.caltech.edu/CaltechAUTHORS:20190328-144424355

[img] PDF - Published Version
See Usage Policy.

1050Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20190328-144424355

Abstract

We present an unsupervised method for learning and recognizing object categories from unlabeled images. Motivated by the existence of highly selective, sparsely firing cells observed in the human medial temporal lobe (MTL), we apply a sparse generative model to the outputs of a biologically faithful model of the primate ventral visual system. In our model, a network of nonlinear neurons learns a sparse representation of its inputs through an unsupervised expectation-maximization process. In recognition, this model is used in a maximum-likelihood manner to classify unseen images, and we find units emerging from learning that respond selectively to specific image categories. A significant advantage of this approach is that there is no need to specify the number of categories present in the training set. We present classification accuracy using three different evaluation metrics.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.5244/c.21.102DOIArticle
ORCID:
AuthorORCID
Koch, Christof0000-0001-6482-8067
Additional Information:We thank Thomas Serre and Minjoon Kouh of MIT for providing the visual system model used here as well as assistance with its operation, and Richard Murray, Jerry Marsden, and Pietro Perona at Caltech and Bruno Olshausen at Berkeley for valuable feedback. This work was funded by a Fannie and John Hertz Foundation Fellowship (to S.W.), as well as by grants from the ONR, NIMH, NSF, and DARPA.
Group:Koch Laboratory (KLAB)
Funders:
Funding AgencyGrant Number
Fannie and John Hertz FoundationUNSPECIFIED
Office of Naval Research (ONR)UNSPECIFIED
NIHUNSPECIFIED
National Institute of Mental Health (NIMH)UNSPECIFIED
NSFUNSPECIFIED
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
Record Number:CaltechAUTHORS:20190328-144424355
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20190328-144424355
Official Citation:S. Waydo and C. Koch. Unsupervised Category Discovery in Images Using Sparse Neural Coding. In N. M. Rajpoot and A. H. Bhalerao, editors, Proceedings of the British Machine Conference, pages 102.1-102.10. BMVA Press, September 2007. doi:10.5244/C.21.102.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94254
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:28 Mar 2019 22:51
Last Modified:28 Mar 2019 22:51

Repository Staff Only: item control page