Published on Mon Nov 14 2016

Automatic discovery of discriminative parts as a quadratic assignment problem

Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frederic Jurie

Part-based image classification consists in representing categories by small sets of discriminative parts. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets.

0
0
0
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. 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.