Multi-task and multi-domain learning with tensor networks

Yash Garg; Ashley Prater-Bennette; M. Salman Asif

doi:10.1117/12.2663623

14 June 2023 Multi-task and multi-domain learning with tensor networks

Yash Garg, Ashley Prater-Bennette, M. Salman Asif

Proceedings Volume 12547, Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII; 125470W (2023) https://doi.org/10.1117/12.2663623
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

We propose a tensor network that can learn to perform multiple tasks by adjusting the factors of each layer. Most of the existing methods for multi-task learning train a single network to extract task-specific features and subsequent prediction. We propose to use a single network with task-specific transformations that can extract task-specific features and perform task inference with small memory overhead. In particular, we transform features using low-rank updates in the convolution kernels. We present experiments on different datasets for multi-task and multi-domain learning and demonstrate that our method achieves state-of-the-art performance with minimal memory overhead compared to existing methods.

Conference Presentation

Citation Download Citation

Yash Garg, Ashley Prater-Bennette, and M. Salman Asif "Multi-task and multi-domain learning with tensor networks", Proc. SPIE 12547, Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII, 125470W (14 June 2023); https://doi.org/10.1117/12.2663623

ACCESS THE FULL ARTICLE

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