Beyond dataset bias: multi-task unaligned shared knowledge transfer

Tommasi, Tatiana, Quadrianto, Novi, Caputo, Barbara and Lampert, Christoph H (2013) Beyond dataset bias: multi-task unaligned shared knowledge transfer. 11th Asian conference on computer vision (ACCV), Daejeon, Korea, 5-9 November, 2012. Published in: Lee, Kyoung Mu, Matsushita, Yasuyuki, Rehg, James M and Hu, Zhanyi, (eds.) Proceedings of Computer vision - ACCV 2012: 11th Asian Conference on Computer Vision; Daejeon, Korea; 5-9 November 2012. (7724) 1-15. Springer Verlag, Berlin; New York. ISSN 0302-9743 ISBN 9783642373305

[img] PDF - Published Version
Restricted to SRO admin only

Download (1MB)


Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new multiclass problem. Our main idea is to identify an image representation that decomposes orthogonally into two subspaces: a part specific to each dataset, and a part generic to, and therefore shared between, all the considered source sets. This allows us to use the generic representation as un-biased reference knowledge for a novel classification task. By casting the method in the multi-view setting, we also make it possible to use different features for different databases. We call the algorithm MUST, Multitask Unaligned Shared knowledge Transfer. Through extensive experiments on five public datasets, we show that MUST consistently improves the cross-datasets generalization performance.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science > Q Science (General)
Depositing User: Novi Quadrianto
Date Deposited: 25 Feb 2014 09:06
Last Modified: 16 Jun 2017 13:07

View download statistics for this item

📧 Request an update