Learning discriminative spatial representation for image classification

Gaurav Sharma 1, 2 Frédéric Jurie 1, 3
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Spatial Pyramid Representation (SPR) [7] introduces spatial layout information to the orderless bag-of-features (BoF) representation. SPR has become the standard and has been shown to perform competitively against more complex methods for incorporating spatial layout. In SPR the image is divided into regular grids. However, the grids are taken as uniform spatial partitions without any theoretical motivation. In this paper, we address this issue and propose to learn the spatial partitioning with the BoF representation. We define a space of grids where each grid is obtained by a series of recursive axis aligned splits of cells. We cast the classification problem in a maximum margin formulation with the optimization being over the weight vector and the spatial grid. In addition to experiments on two challenging public datasets (Scene-15 and Pascal VOC 2007) showing that the learnt grids consistently perform better than the SPR while being much smaller in vector length, we also introduce a new dataset of human attributes and show that the current method is well suited to the recognition of spatially localized human attributes.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download


https://hal.inria.fr/hal-00722820
Contributor : Thoth Team <>
Submitted on : Saturday, August 4, 2012 - 2:58:40 PM
Last modification on : Thursday, February 7, 2019 - 5:31:35 PM
Long-term archiving on : Friday, December 16, 2016 - 5:09:07 AM

Files

bmvc_final.pdf
Files produced by the author(s)

Identifiers

Citation

Gaurav Sharma, Frédéric Jurie. Learning discriminative spatial representation for image classification. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. pp.1-11, ⟨10.5244/C.25.6⟩. ⟨hal-00722820⟩

Share

Metrics

Record views

1010

Files downloads

1042