Discrimintive Image Warping with Attribute Flow

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. Disciplines Computer Sciences Comments Zhang, W., Srinivasan, P., Shi, J. IEEE Conference on Computer Vision and Pattern Recognition. 2011. ©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Digital Object Identifier : 10.1109/CVPR.2011.5995342 This conference paper is available at ScholarlyCommons: http://repository.upenn.edu/cis_papers/530 Discriminative Image Warping with Attribute Flow Weiyu Zhang, Praveen Srinivasan GRASP Laboratory, University of Pennsylvania 3330 Walnut St., Philadelphia, PA 19104 {zhweiyu, psrin}@seas.upenn.edu Jianbo Shi GRASP Laboratory, University of Pennsylvania 3330 Walnut St., Philadelphia, PA 19104 [email protected]