Spotlight the Negatives: A Generalized Discriminative Latent Model
2015 (English)Conference paper (Refereed)
Discriminative latent variable models (LVM) are frequently applied to various visualrecognition tasks. In these systems the latent (hidden) variables provide a formalism formodeling structured variation of visual features. Conventionally, latent variables are de-fined on the variation of the foreground (positive) class. In this work we augment LVMsto includenegativelatent variables corresponding to the background class. We formalizethe scoring function of such a generalized LVM (GLVM). Then we discuss a frameworkfor learning a model based on the GLVM scoring function. We theoretically showcasehow some of the current visual recognition methods can benefit from this generalization.Finally, we experiment on a generalized form of Deformable Part Models with negativelatent variables and show significant improvements on two different detection tasks.
Place, publisher, year, edition, pages
Research subject Computer Science
IdentifiersURN: urn:nbn:se:kth:diva-172138OAI: oai:DiVA.org:kth-172138DiVA: diva2:845952
British Machine Vision Conference (BMVC),7-10 September, Swansea, UK, 2015
QC 201508282015-08-132015-08-132016-09-08Bibliographically approved