Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these datasets.
@article{arxiv.1611.04413,
title = {Automatic discovery of discriminative parts as a quadratic assignment problem},
author = {Ronan Sicre and Julien Rabin and Yannis Avrithis and Teddy Furon and Frederic Jurie},
journal= {arXiv preprint arXiv:1611.04413},
year = {2016}
}