000192742 001__ 192742
000192742 005__ 20190125163144.0
000192742 037__ $$aREP_WORK
000192742 088__ $$aIdiap-RR-25-2011
000192742 245__ $$aMulticlass Transfer Learning from Unconstrained Priors
000192742 269__ $$a2011
000192742 260__ $$bIdiap$$c2011
000192742 336__ $$aReports
000192742 520__ $$aThe vast majority of transfer learning methods proposed in the visual recognition domain over the last years ad- dresses the problem of object category detection, assuming a strong control over the priors from which transfer is done. This is a strict condition, as it concretely limits the use of this type of approach in several settings: for instance, it does not allow in general to use off-the-shelf models as priors. Moreover, the lack of a multiclass formulation for most of the existing transfer learning algorithms prevents using them for object categorization problems, where their use might be beneficial, especially when the number of categories grows and it becomes harder to get enough annotated data for training standard learning methods. This paper presents a multiclass transfer learning algorithm that allows to take advantage of priors built over different features and with different learning methods than the one used for learning the new task. We use the priors as experts, and transfer their outputs to the new incoming samples as additional information. We cast the learning problem within the Multi Kernel Learning framework. The resulting formulation solves efficiently a joint optimization problem that determines from where and how much to trans- fer, with a principled multiclass formulation. Extensive experiments illustrate the value of this approach.
000192742 700__ $$0243366$$aLuo, Jie$$g178013
000192742 700__ $$0243360$$aTommasi, Tatiana$$g184489
000192742 700__ $$0243991$$aCaputo, Barbara$$g190271
000192742 8564_ $$s825438$$uhttps://infoscience.epfl.ch/record/192742/files/Luo_Idiap-RR-25-2011.pdf$$yn/a$$zn/a
000192742 909C0 $$0252189$$pLIDIAP$$xU10381
000192742 909CO $$ooai:infoscience.tind.io:192742$$pSTI$$preport$$qGLOBAL_SET
000192742 937__ $$aEPFL-REPORT-192742
000192742 970__ $$aLuo_Idiap-RR-25-2011/LIDIAP
000192742 973__ $$aEPFL
000192742 980__ $$aREPORT