Skip to Main content Skip to Navigation
Journal articles

Weakly supervised learning of visual models and its application to content-based retrieval

Cordelia Schmid 1, *
* Corresponding author
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a method for weakly supervised learning of visual models. The visual model is based on a two-layer image description: a set of "generic" descriptors and their distribution over neighbourhoods. "Generic" descriptors represent sets of similar rotational invariant feature vectors. Statistical spatial constraints describe the neighborhood structure and make our description more discriminant. The joint probability of the frequencies of "generic" descriptors over a neighbourhood is multi-modal and is represented by a set of "neighbourhood-frequency" clusters. Our image description is rotationally invariant, robust to model deformations and characterizes efficiently "appearance-based" visual structure. The selection of distinctive clusters determines model features (common to the positive and rare in the negative examples). Visual models are retrieved and localized using a probabilistic score. Experimental results for "textured" animals and faces show a very good performance for retrieval as well as localization.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/inria-00548553
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 9:09:43 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM
Long-term archiving on: : Monday, March 21, 2011 - 3:17:07 AM

File

schmid_ijcv2004.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Cordelia Schmid. Weakly supervised learning of visual models and its application to content-based retrieval. International Journal of Computer Vision, Springer Verlag, 2004, Special Issue on Content-Based Image Retrieval, 56 (1), pp.7--16. ⟨10.1023/B:VISI.0000004829.38247.b0⟩. ⟨inria-00548553⟩

Share

Metrics

Record views

402

Files downloads

764