Automatic Discovery of Discriminative Parts as a Quadratic Assignment Problem

Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frederic Jurie, Ewa Kijak; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1059-1068

Abstract


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. We propose to cast the training of parts 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Sicre_2017_ICCV,
author = {Sicre, Ronan and Rabin, Julien and Avrithis, Yannis and Furon, Teddy and Jurie, Frederic and Kijak, Ewa},
title = {Automatic Discovery of Discriminative Parts as a Quadratic Assignment Problem},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}