Semi-supervised learning in gigantic image collections

Rob Fergus*, Yair Weiss, Antonio Torralba

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

198 Scopus citations

Abstract

With the advent of the Internet it is now possible to collect hundreds of millions of images. These images come with varying degrees of label information. "Clean labels" can be manually obtained on a small fraction, "noisy labels" may be extracted automatically from surrounding text, while for most images there are no labels at all. Semi-supervised learning is a principled framework for combining these different label sources. However, it scales polynomially with the number of images, making it impractical for use on gigantic collections with hundreds of millions of images and thousands of classes. In this paper we show how to utilize recent results in machine learning to obtain highly efficient approximations for semi-supervised learning that are linear in the number of images. Specifically, we use the convergence of the eigenvectors of the normalized graph Laplacian to eigenfunctions of weighted Laplace-Beltrami operators. Our algorithm enables us to apply semi-supervised learning to a database of 80 million images gathered from the Internet.

Original languageAmerican English
Title of host publicationAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference
PublisherNeural Information Processing Systems
Pages522-530
Number of pages9
ISBN (Print)9781615679119
StatePublished - 2009
Event23rd Annual Conference on Neural Information Processing Systems, NIPS 2009 - Vancouver, BC, Canada
Duration: 7 Dec 200910 Dec 2009

Publication series

NameAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

Conference

Conference23rd Annual Conference on Neural Information Processing Systems, NIPS 2009
Country/TerritoryCanada
CityVancouver, BC
Period7/12/0910/12/09

Fingerprint

Dive into the research topics of 'Semi-supervised learning in gigantic image collections'. Together they form a unique fingerprint.

Cite this