U-TELL: Unsupervised Task Expert Lifelong Learning

Page view(s)
11
Checked on Feb 06, 2025
U-TELL: Unsupervised Task Expert Lifelong Learning
Title:
U-TELL: Unsupervised Task Expert Lifelong Learning
Journal Title:
International Conference on Image Processing
Publication Date:
07 October 2024
Citation:
Solomon, I., Aung, A. P. P., Kumar, U., & Jayavelu, S. (2024, October). U-Tell: Unsupervised Task Expert Lifelong Learning. In 2024 IEEE International Conference on Image Processing (ICIP) (pp. 1057-1063). IEEE.
Abstract:
Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label information and these models suffer from catastrophic forgetting. To address these issues, we propose an unsupervised CL model with task experts called Unsupervised Task Expert Lifelong Learning (U-TELL) to continually learn the data arriving in a sequence addressing catastrophic forgetting. During training of U-TELL, we introduce a new expert on arrival of a new task. Our proposed architecture has task experts, a structured data generator and a task assigner. Each task expert is composed of 3 blocks; i) a variational autoencoder to capture the task distribution and perform data abstraction, ii) a k-means clustering module, and iii) a structure extractor to preserve latent task data signature. During testing, task assigner selects a suitable expert to perform clustering. U-TELL does not store or replay task samples, instead, we use generated structured samples to train the task assigner. We compared U-TELL with five SOTA CL methods. U-TELL outperformed all baselines on seven benchmarks and one industry dataset for various CL scenarios with a training time over 6 times faster than the best performing baseline.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - Accelerated Materials Development for Manufacturing Programme
Grant Reference no. : A1898b0043
Description:
© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2169-3536
Files uploaded:

File Size Format Action
utell.pdf 522.42 KB PDF Request a copy