PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Semi-Supervised Learning in Gigantic Image Collections
Rob Fergus, Yair Weiss and Antonio Torralba
Advances in Neural Information Processing Systems (NIPS) 2009.


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 ex- tracted 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 uti- lize 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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
ID Code:5636
Deposited By:Talya Meltzer
Deposited On:08 March 2010