Learning The Discriminative Power-Invariance Trade-Off
Top Cited Papers
- 1 January 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
- https://doi.org/10.1109/iccv.2007.4408875
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 Cal- tech 101 datasets.Keywords
This publication has 40 references indexed in Scilit:
- Fast Transformation-Invariant Component AnalysisInternational Journal of Computer Vision, 2007
- Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive StudyInternational Journal of Computer Vision, 2006
- Efficient Hyperkernel Learning Using Second-Order Cone ProgrammingIEEE Transactions on Neural Networks, 2006
- Learning silhouette features for control of human motionACM Transactions on Graphics, 2005
- A Statistical Approach to Texture Classification from Single ImagesInternational Journal of Computer Vision, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Boosting Image RetrievalInternational Journal of Computer Vision, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Learning texture discrimination masksIeee Transactions On Pattern Analysis and Machine Intelligence, 1996
- Projected gradient methods for linearly constrained problemsMathematical Programming, 1987