Beyond dataset bias: Multi-task unaligned shared knowledge transfer

T. Tommasi, N. Quadrianto, B. Caputo, C. Lampert, 7724 (2013) 1–15.

Download
OA 1.51 MB

Conference Paper | Published | English
Author
; ; ;
Department
Series Title
LNCS
Abstract
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.
Publishing Year
Date Published
2013-04-04
Acknowledgement
This work was supported by the PASCAL 2 Network of Excellence (TT) and by the Newton International Fellowship (NQ)
Volume
7724
Page
1 - 15
Conference
ACCV: Asian Conference on Computer Vision
Conference Location
Daejeon, Korea
Conference Date
2012-11-05 – 2012-11-09
IST-REx-ID

Cite this

Tommasi T, Quadrianto N, Caputo B, Lampert C. Beyond dataset bias: Multi-task unaligned shared knowledge transfer. 2013;7724:1-15. doi:10.1007/978-3-642-37331-2_1
Tommasi, T., Quadrianto, N., Caputo, B., & Lampert, C. (2013). Beyond dataset bias: Multi-task unaligned shared knowledge transfer. Presented at the ACCV: Asian Conference on Computer Vision, Daejeon, Korea: Springer. https://doi.org/10.1007/978-3-642-37331-2_1
Tommasi, Tatiana, Novi Quadrianto, Barbara Caputo, and Christoph Lampert. “Beyond Dataset Bias: Multi-Task Unaligned Shared Knowledge Transfer.” Lecture Notes in Computer Science. Springer, 2013. https://doi.org/10.1007/978-3-642-37331-2_1.
T. Tommasi, N. Quadrianto, B. Caputo, and C. Lampert, “Beyond dataset bias: Multi-task unaligned shared knowledge transfer,” vol. 7724. Springer, pp. 1–15, 2013.
Tommasi T, Quadrianto N, Caputo B, Lampert C. 2013. Beyond dataset bias: Multi-task unaligned shared knowledge transfer. 7724, 1–15.
Tommasi, Tatiana, et al. Beyond Dataset Bias: Multi-Task Unaligned Shared Knowledge Transfer. Vol. 7724, Springer, 2013, pp. 1–15, doi:10.1007/978-3-642-37331-2_1.
Main File(s)
File Name
Access Level
OA Open Access
Last Uploaded
2019-01-22T14:03:11Z


Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar