Discriminative ImageWarping With Attribute Flow
The authors 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. They introduce the concept of attribute flow which explicitly models how image attributes vary with its deformation. They develop a non-parametric method to approximate this using histogram matching, which can be solved efficiently using linear programming. Their 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 they can accurately recognize highly deformable objects with few training examples.