Multitask Learning with Heterogeneous Tasks
- Authors
- Kim, C.; Kim, Eunwoo
- Issue Date
- Oct-2022
- Publisher
- IEEE Computer Society
- Keywords
- heterogeneous tasks; Multitask learning; resource efficiency
- Citation
- International Conference on ICT Convergence, v.2022-October, pp 1024 - 1026
- Pages
- 3
- Journal Title
- International Conference on ICT Convergence
- Volume
- 2022-October
- Start Page
- 1024
- End Page
- 1026
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/61185
- DOI
- 10.1109/ICTC55196.2022.9952681
- ISSN
- 2162-1233
- Abstract
- It is general that more computation resources are required to achieve better performance of CNNs. This is even more severe when we perform multiple tasks. Multitask learning (MTL) can address this problem by sharing architecture across tasks. Previous MTL studies obtained a feature from a shared backbone or module and performed multiple tasks. However, learning from heterogeneous tasks has not gained much attention. For example, input data has different properties, such as resolutions and object classes; thus, the aggregation of the features generated from heterogeneous tasks is complicated. To mitigate this problem, we propose a simple learning strategy that generalizes the shared representation using multiple datasets for heterogeneous tasks. We evaluate the strategy using four datasets and show that learning from different tasks jointly gives a comparable performance to learning individual tasks and outperforms the existing strategy for some tasks. © 2022 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/61185)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.