• Documents
  • Authors
  • Tables
  • Other Seers ▼
    RefSeer AckSeer CollabSeer SeerSeer
  • Log in
  • Sign up
  • MetaCart

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

Learning the discriminative powerinvariance trade-off (2007)

Cached

  • Download as a PDF

Download Links

  • [gip.cs.technion.ac.il]
  • [research.microsoft.com]
  • [www.research.microsoft.com]
  • [research.microsoft.com]
  • [www.research.microsoft.com]
  • [research.microsoft.com]
  • [www.cs.huji.ac.il]

  • Save to List
  • Add to Collection
  • Correct Errors
  • Monitor Changes
by Manik Varma
Venue:In ICCV
Citations:80 - 3 self
  • Summary
  • Active Bibliography
  • Co-citation
  • Clustered Documents
  • Version History

Versions

  • Version 0
  • Version 1

Version History

Metadata Version 1

DatumValueSource
TITLE Learning the discriminative powerinvariance trade-off INFERENCE
AUTHOR NAME Manik Varma SVM HeaderParse 0.2
AUTHOR AFFIL Microsoft Research India SVM HeaderParse 0.2
ABSTRACT We investigate the problem of learning optimal descriptors for a given classification task. Many hand-crafted descriptors have been proposed in the literature for measuring visual similarity. Looking past initial differences, what really distinguishes one descriptor from another is the tradeoff that it achieves between discriminative power and invariance. Since this trade-off must vary from task to task, no single descriptor can be optimal in all situations. Our focus, in this paper, is on learning the optimal tradeoff for classification given a particular training set and prior constraints. The problem is posed in the kernel learning framework. We learn the optimal, domain-specific kernel as a combination of base kernels corresponding to base features which achieve different levels of trade-off (such as no invariance, rotation invariance, scale invariance, affine invariance, etc.) This leads to a convex optimisation problem with a unique global optimum which can be solved for efficiently. The method is shown to achieve state-of-the-art performance on the UIUC textures, Oxford flowers and Caltech 101 datasets. 1. SVM HeaderParse 0.2
YEAR 2007 INFERENCE
VENUE In ICCV INFERENCE
VENUE TYPE CONFERENCE INFERENCE
CITATIONS 51 found ParsCit 1.0
The National Science Foundation
  • About CiteSeerX
  • Submit Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2010 The Pennsylvania State University