1 / 19

Learning from Multiple Outlooks

Learning from Multiple Outlooks. Maayan Harel and Shie Mannor ICML 2011 Presented by Minhua Chen. What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms CVPR2011. Introduction.

anoush
Download Presentation

Learning from Multiple Outlooks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Learning from Multiple Outlooks MaayanHarel and ShieMannor ICML 2011 Presented by Minhua Chen

  2. What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms CVPR2011

  3. Introduction • A learning task often relates to multiple representations, or called domains, outlooks. • For example, in activity recognition, each user (outlook) may use different sensors. • There are no sample correspondence, nor feature correspondence across outlooks; only the label space (classification task) is shared. • The goal is to use the information in all outlooks to improve learning performance. • The approach is to map the data in one outlook (source) to another (target), so that the effective sample size is enlarged in the target domain.

  4. Labeled data (*) and unlabeled data in the target domain (square)

  5. Classifier trained on labeled data in the target domain

  6. Labeled data from the source domain comes in (+).

  7. New classifier trained on both labeled target data and transferred source data.

  8. Problem Formulation • The central question is how to map data from one domain to the other, possibly with different feature dimensions. • The authors proposed an algorithm that computes optimal affine mapping by matching moments of the empirical distribution for each class. Source domain Target domain

  9. Mathematical Solution • Procrustes analysis can be applied to solve Ri. • The formulation can be extended to multiple outlooks:

  10. Experiments • Activity recognition task with the following human activities: walking, running, going upstairs, going downstairs, lingering. • Data recorded by different users are regarded as different outlooks (domains), since the sensors used are different. • Two setups are examined: domain adaptation with shared feature space, and multiple outlooks with different feature spaces. • The authors tested the success of the mapping algorithm by classification of the target test data with a SVM classifier trained on the mapped source data.

  11. with the same feature space for all domains.

  12. with the same feature space for all domains.

  13. What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms B. Kulis, K. Saenko and T. Darrel, CVPR 2011

  14. Main Idea

  15. Kernelization

More Related