Discrimintive Image Warping with Attribute Flow

Loading...
Thumbnail Image
Penn collection
Center for Human Modeling and Simulation
Degree type
Discipline
Subject
Computer Sciences
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Zhang, Weiyu
Srinivasan, Praveen
Contributor
Abstract

We address the problem of finding deformation between two images for the purpose of recognizing objects. The challenge is that discriminative features are often transformation-variant (e.g. histogram of oriented gradients, texture), while transformation-invariant features (e.g. intensity, color) are often not discriminative. We introduce the concept of attribute flow which explicitly models how image attributes vary with its deformation. We develop a non-parametric method to approximate this using histogram matching, which can be solved efficiently using linear programming. Our method produces dense correspondence between images, and utilizes discriminative, transformation-variant features for simultaneous detection and alignment. Experiments on ETHZ shape categories dataset show that we can accurately recognize highly deformable objects with few training examples.

Advisor
Date of presentation
2011-01-01
Conference name
Center for Human Modeling and Simulation
Conference dates
2023-05-17T07:08:53.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Zhang, W., Srinivasan, P., Shi, J. IEEE Conference on Computer Vision and Pattern Recognition. 2011.
Recommended citation
Collection