Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

1-2019

Abstract

Multi-task learning is popular in machine learning and computer vision. In multitask learning, properly modeling task relations is important for boosting the performance of jointly learned tasks. Task covariance modeling has been successfully used to model the relations of tasks but is limited to homogeneous multi-task learning. In this paper, we propose a feature based task relation modeling approach, suitable for both homogeneous and heterogeneous multi-task learning. First, we propose a new metric to quantify the relations between tasks. Based on the quantitative metric, we then develop the task relation layer, which can be combined with any deep learning architecture to form task relation networks to fully exploit the relations of different tasks in an online fashion. Benefiting from the task relation layer, the task relation networks can better leverage the mutual information from the data. We demonstrate our proposed task relation networks are effective in improving the performance in both homogeneous and heterogeneous multi-task learning settings through extensive experiments on computer vision tasks.

Discipline

Graphics and Human Computer Interfaces | OS and Networks

Areas of Excellence

Digital transformation

Publication

Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, January 7-11

First Page

1

Last Page

9

ISBN

9781728119762

Identifier

10.1109/WACV.2019.00104

Publisher

IEEE

City or Country

Piscataway, NJ

Additional URL

https://doi.org/10.1109/WACV.2019.00104

Download

Share

COinS