Improving feature generalizability with multitask learning in class incremental learning
Many deep learning applications, like keyword spotting [1], [2], require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving as much of the old knowledge as possible while lear...
Saved in:
Main Authors: | MA, Dong, TANG, Chi Ian, MASCOLO, Cecilia |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7305 https://ink.library.smu.edu.sg/context/sis_research/article/8308/viewcontent/2204.12915.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Revisiting class-incremental learning with pre-trained models: generalizability and adaptivity are all you need
by: Zhou, Da-Wei, et al.
Published: (2024) -
INCREMENTAL LEARNING IN NON-STATIONARY ENVIRONMENTS
by: ABHINIT KUMAR AMBASTHA
Published: (2023) -
Collaborative online ranking algorithms for multitask learning
by: LI, Guangxia, et al.
Published: (2019) -
Edge-computing-based knowledge distillation and multitask learning for partial discharge recognition
by: Ji, Jinsheng, et al.
Published: (2024) -
ACIL: analytic class-incremental learning with absolute memorization and privacy protection
by: Zhuang, Huiping, et al.
Published: (2024)