Category level object segmentation - learning to segment objects with latent aspect models

Diane Larlus 1 Frédéric Jurie 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We propose a new method for learning to segment objects in images. This method is based on a latent variables model used for representing images and objects, inspired by the LDA model. Like the LDA model, our model is capable of automatically discovering which visual information comes from which object. We extend LDA by considering that images are made of multiple overlapping regions, treated as distinct documents, giving more chance to small objects to be discovered. This model is extremely well suited for assigning image patches to objects (even if they are small), and therefore for segmenting objects. We apply this method on objects belonging to categories with high intra-class variations and strong viewpoint changes.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download


https://hal.inria.fr/inria-00548681
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:28:44 AM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on : Monday, November 5, 2012 - 2:41:02 PM

Files

LJ07.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00548681, version 1

Collections

Citation

Diane Larlus, Frédéric Jurie. Category level object segmentation - learning to segment objects with latent aspect models. VISAPP - 2nd International Conference on Computer Vision Theory and Applications, Mar 2007, Barcelona, Spain. pp.122-127. ⟨inria-00548681⟩

Share

Metrics

Record views

683

Files downloads

486