Patch-level spatial layout for classification and weakly supervised localization - Archive ouverte HAL Access content directly
Conference Papers Year :

Patch-level spatial layout for classification and weakly supervised localization

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

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⟩
262 View
302 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More