Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Reports, Documentation, and Standards
  4. Constructing visual models with a latent space approach
 
Loading...
Thumbnail Image
report

Constructing visual models with a latent space approach

Monay, Florent
•
Quelhas, Pedro
•
Gatica-Perez, Daniel  
Show more
2005

We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns of visual co-occurrence and if the learned visual models improve performance when less labeled data are available. We present and discuss results that support these hypotheses. Probabilistic Latent Semantic Analysis (PLSA) automatically identifies aspects from the data with semantic meaning, producing unsupervised soft clustering. The resulting compact representation retains sufficient discriminative information for accurate object classification, and improves the classification accuracy through the use of unlabeled data when less labeled training data are available. We perform experiments on a 7-class object database containing 1776 images.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

monay-idiap-rr-05-14.pdf

Access type

openaccess

Size

435.66 KB

Format

Adobe PDF

Checksum (MD5)

c4312c6520f763fdddd615f216c38e73

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés