Adaptive aggregation networks for class-incremental learning
Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase. An inherent problem in CIL is the stability-plasticity dilemma between the learning of old and new classes, i.e., high-plasticity models easily forget old classes, but high-sta...
Saved in:
Main Authors: | LIU, Yaoyao, SCHIELE, Bernt, SUN, Qianru |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6119 https://ink.library.smu.edu.sg/context/sis_research/article/7122/viewcontent/CVPR2021_Adaptive_Aggregation_Networks_for_Class_Incremental_Learning__1_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
DeshadowNet: A multi-context embedding deep network for shadow removal
by: QU, Liangqiong, et al.
Published: (2017) -
Online hyperparameter optimization for class-incremental learning
by: LIU, Yaoyao, et al.
Published: (2023) -
Wakening past concepts without past data: Class-incremental learning from online placebos
by: LIU, Yaoyao, et al.
Published: (2024) -
Building deep networks on grassmann manifolds
by: HUANG, Zhiwu, et al.
Published: (2018) -
RMM: Reinforced memory management for class-incremental learning
by: LIU, Yaoyao, et al.
Published: (2021)