University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Image Classification Using a Background Prior

Image Classification Using a Background Prior

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending

A canonical problem in computer vision is category classification (e.g. find all instances of human faces, cars etc., in an image). Typically, the input for training a classifier is a relatively small sample of positive examples, and a much larger sample of negative examples, which in current applications can consist of images from thousands of categories. The difficulty of the problem sharply increases with the dimension and size of the negative example set. In this talk I will describe an efficient and easy to apply classification algorithm, which replaces the negative samples by a prior and then constructs a “hybrid” classifier which separates the positive samples from this prior. The resulting classifier achieves an identical or better classification rate than SVM , while requiring far smaller memory and lower computational complexity to train and apply. While here it is applied to image classes, the idea is general and can be applied to other domains. Joint work with Margarita Osadchy and Bella Fadida-Specktor. An early version of this work was presented in ECCV 2012 .

This talk is part of the Microsoft Research Cambridge, public talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity