Transfer Learning from Multiple Sources

Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classifier for a target domain, where the available data is scarce. The effectiveness of the transfer is affected by the relationship between source and target. Rather than improving the learning, brute force leveraging of a source poorly related to the target may decrease the classifier performance. One strategy to reduce this negative transfer is to import knowledge from multiple sources to increase the chance of finding one source closely related to the target. In (Yao & Doretto, 2010) these ideas are explored by extending the boosting framework for transferring knowledge from multiple sources. It turns out that it is possible to obtain algorithms that are very efficient in terms of the speed with which they can be retrained once a new target domain is given. Such algorithms have been applied to very important computer vision problems such as object category recognition and specific object detection.

References

1. CVPR

   Boosting for transfer learning with multiple sources Yao, Y., and Doretto, G. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010. abstract bibTeX pdf

   Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classi- fier for a target domain, where the available data is scarce. The effectiveness of the transfer is affected by the relation- ship between source and target. Rather than improving the learning, brute force leveraging of a source poorly related to the target may decrease the classifier performance. One strategy to reduce this negative transfer is to import knowl- edge from multiple sources to increase the chance of find- ing one source closely related to the target. This work ex- tends the boosting framework for transferring knowledge from multiple sources. Two new algorithms, MultiSource- TrAdaBoost, and TaskTrAdaBoost, are introduced, analyzed, and applied for object category recognition and specific ob- ject detection. The experiments demonstrate their improved performance by greatly reducing the negative transfer as the number of sources increases. TaskTrAdaBoost is a fast algorithm enabling rapid retraining over new targets.

   @inproceedings{yaoD10cvpr,
     abbr = {CVPR},
     author = {Yao, Y. and Doretto, G.},
     title = {Boosting for transfer learning with multiple sources},
     booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision
     	and Pattern Recognition},
     year = {2010},
     bib2html_pubtype = {Conferences},
     bib2html_rescat = {Object Classification},
     file = {yaoD10cvpr.pdf:doretto\\conference\\yaoD10cvpr.pdf:PDF;wangDSRT07iccv.pdf:doretto\\conference\\wangDSRT07iccv.pdf:PDF},
     owner = {doretto},
     timestamp = {2008.01.19}
   }