\\

\\

http://cs.nyu.edu/~fergus/ssl.png |

Humans can only ever hope to manually tag a tiny fraction of the images on the Internet. Using semi-supervised learning methods we can propagate these sparse labels to unlabeled images. The challenge is doing this when we have billions of unlabeled images.

Semi-Supervised Learning for Gigantic Image Collections

http://cs.nyu.edu/~fergus/poster2.png |

80 Million Tiny Images

One recent direction of investigation is in a "brute force" approach to recognition, using a dataset of 80 million images gathered from the web. By using overwhelming amounts of data, very simple algorithms can perform surprisingly well.

Improving Image Search Engines

http://cs.nyu.edu/~fergus/poster2.png | 80 Million Tiny Images

One recent direction of investigation, is in a "brute force" approach to recognition, using a dataset of 80 million images gathered from the web. By using overwhelming amounts of data, very simple algorithms can perform surprisingly well.

http://cs.nyu.edu/~fergus/airplane_query2.jpg |

Internet Vision

Semi-Supervised Learning for Gigantic Image Collections

Large-Scale Retrieval?

Construction of compact binary descriptiors for vison

Brute Force Recognition

Another, more recent direction of investigation, is in "brute force" approaches to recognition, using 100's of millions of images gathered from the web. By using overwhelming amounts of data, very simple algorithms can perform surprisingly well. Blurb on Tiny images.

Improving Image Search Engines

One possibility is to use Internet image search engines to provide a diverse set of images from which object category models may be trained. In turn, these models may be applied to collections of images from the Internet or elsewhere, enabling search by visual content (known as content-based image retrieval, CBIR), rather than the text-based searches that are currently employed.