Learning to rank using privileged information Conference Paper


Author(s): Sharmanska, Viktoriia; Quadrianto, Novi; Lampert, Christoph
Title: Learning to rank using privileged information
Affiliation IST Austria
Abstract: Many computer vision problems have an asymmetric distribution of information between training and test time. In this work, we study the case where we are given additional information about the training data, which however will not be available at test time. This situation is called learning using privileged information (LUPI). We introduce two maximum-margin techniques that are able to make use of this additional source of information, and we show that the framework is applicable to several scenarios that have been studied in computer vision before. Experiments with attributes, bounding boxes, image tags and rationales as additional information in object classification show promising results.
Keywords: Learning to rank; object classification; privileged information during training
Conference Title: ICCV: International Conference on Computer Vision
Conference Dates: December 1 - 8, 2013
Conference Location: Sydney, Australia
Publisher: IEEE  
Date Published: 2013-12-01
Start Page: 825
End Page: 832
Sponsor: This work was in parts funded by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007- 2013)/ERC grant agreement no 308036. NQ is supported by the Newton International Fellowship.
DOI: 10.1109/ICCV.2013.107
Open access: no
IST Austria Authors
  1. Christoph Lampert
    87 Lampert
Related IST Austria Work