 |
Conference papers
Automatic discovery of discriminative parts as a quadratic assignment problem
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.
Cited literature [42 references]
https://hal.archives-ouvertes.fr/hal-01623148
Contributor : Frederic Jurie <>
Submitted on : Wednesday, October 25, 2017 - 9:51:56 AM
Last modification on : Friday, January 8, 2021 - 3:39:55 AM
Long-term archiving on: : Friday, January 26, 2018 - 12:39:55 PM
Contributor : Frederic Jurie <>
Submitted on : Wednesday, October 25, 2017 - 9:51:56 AM
Last modification on : Friday, January 8, 2021 - 3:39:55 AM
Long-term archiving on: : Friday, January 26, 2018 - 12:39:55 PM
File
ICCV17W_quadraParts.pdf
Files produced by the author(s)