Automatic discovery of discriminative parts as a quadratic assignment problem

Ronan Sicre 1 Julien Rabin 2 Yannis Avrithis 1 Teddy Furon 1 Frédéric Jurie 2
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download
Contributor : Yannis Avrithis <>
Submitted on : Tuesday, November 19, 2019 - 1:43:32 PM
Last modification on : Wednesday, December 4, 2019 - 3:22:26 PM


Files produced by the author(s)


  • HAL Id : hal-02370324, version 1
  • ARXIV : 1611.04413


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



Record views


Files downloads