Automatic discovery of discriminative parts as a quadratic assignment problem - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Automatic discovery of discriminative parts as a quadratic assignment problem

(1) , (2) , (1) , (1) , (2)
1
2

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.
Fichier principal
Vignette du fichier
1611.04413.pdf (2.01 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02370324 , version 1 (19-11-2019)

Identifiers

Cite

Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frédéric Jurie. Automatic discovery of discriminative parts as a quadratic assignment problem. 2016. ⟨hal-02370324⟩
43 View
117 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More