Transfer Learning Through Greedy Subset Selection

We study the binary transfer learning problem, focusing on how to select sources from a large pool and how to combine them to yield a good performance on a target task. In particular, we consider the transfer learning setting where one does not have direct access to the source data, but rather employs the source hypotheses trained from them. Building on the literature on the best subset selection problem, we propose an efficient algorithm that selects relevant source hypotheses and feature dimensions simultaneously. On three computer vision datasets we achieve state-of-the-art results, substantially outperforming transfer learning and popular feature selection baselines in a small-sample setting. Also, we theoretically prove that, under reasonable assumptions on the source hypotheses, our algorithm can learn effectively from few examples.


Editor(s):
Murino, V
Puppo, E
Published in:
Image Analysis And Processing - Iciap 2015, Pt I, 9279, 3-14
Presented at:
18th International Conference on Image Analysis and Processing (ICIAP), Genoa, ITALY, SEP 07-11, 2015
Year:
2015
Publisher:
Cham, Springer Int Publishing Ag
ISSN:
0302-9743
ISBN:
978-3-319-23231-7
978-3-319-23230-0
Laboratories:




 Record created 2016-02-16, last modified 2018-05-09


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)