CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 13034 > Article
Presentation + Paper
7 June 2024 BSMO: enhancing multitask learning through batch swapping optimization
Zephaniah Spencer, Gunar Schirner, Hamed Tabkhi
Author Affiliations +
Proceedings Volume 13034, Real-Time Image Processing and Deep Learning 2024; 1303409 (2024) https://doi.org/10.1117/12.3013609
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States
Abstract
With the advent of deep learning, there has been an ever-growing list of applications to which Deep Convolutional Neural Networks (DCNNs) can be applied. The field of Multi-Task Learning (MTL) attempts to provide optimizations to many-task systems, improving performance by optimization algorithms and structural changes to these networks. However, we have found that current MTL optimization algorithms often impose burdensome computation overheads, require meticulously labeled datasets, and do not adapt to tasks with significantly different loss distributions. We propose a new MTL optimization algorithm: Batch Swapping with Multiple Optimizers (BSMO). We utilize single-task labeled data to train on a multi-task hard parameter sharing (HPS) network through swapping tasks at the batch level. This dramatically increases the flexibility and scalability of training on an HPS network by allowing for per-task datasets and augmentation pipelines. We demonstrate the efficacy of BSMO versus current SOTA algorithms by benchmarking across contemporary benchmarks & networks.
Conference Presentation
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Zephaniah Spencer, Gunar Schirner, and Hamed Tabkhi "BSMO: enhancing multitask learning through batch swapping optimization", Proc. SPIE 13034, Real-Time Image Processing and Deep Learning 2024, 1303409 (7 June 2024); https://doi.org/10.1117/12.3013609
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 9 PAGES + PRESENTATION
DOWNLOAD PAPER SAVE TO MY LIBRARY
WATCH
PRESENTATION
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Mathematical optimization
Artificial intelligence
Computer vision technology
Convolutional neural networks
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top