Learning the discriminative powerinvariance trade-off

Learning the discriminative powerinvariance trade-off (2007)

by Manik Varma

Venue:	In ICCV
Citations:	80 - 3 self

Datum	Value	Source
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