Patch-level spatial layout for classification and weakly supervised localization - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2015

Patch-level spatial layout for classification and weakly supervised localization

Abstract

We propose a discriminative patch-level spatial layout model suitable for training with weak supervision. We start from a block-sparse model of patch appearance based on the normalized Fisher vector representation. The appearance model is responsible for i) selecting a discriminative subset of visual words, and ii) identifying distinctive patches assigned to the selected subset. These patches are further filtered by a sparse spatial model operating on a novel representation of pairwise patch layout. We have evaluated the proposed pipeline in image classification and weakly supervised localization experiments on a public traffic sign dataset. The results show significant advantage of the proposed spatial model over state of the art appearance models.
Fichier principal
Vignette du fichier
main68.pdf (1.18 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01186677 , version 1 (27-08-2015)

Identifiers

Cite

Valentina Zadrija, Josip Krapac, Jakob Verbeek, Siniša Šegvić. Patch-level spatial layout for classification and weakly supervised localization. GCPR - 37th German Conference on Pattern Recognition, Oct 2015, Aachen, Germany. pp.492-503, ⟨10.1007/978-3-319-24947-6_41⟩. ⟨hal-01186677⟩
272 View
351 Download

Altmetric

Share

More