Correlation-Based Knowledge Distillation in Exemplar-Free Class-Incremental Learning

Class-incremental learning (CIL) aims to learn a family of classes incrementally with data available in order rather than training all data at once. One main drawback of CIL is that standard deep neural networks suffer from catastrophic forgetting (CF), especially when the model only has access to d...

Full description

Saved in:
Bibliographic Details
Main Authors: Zijian Gao, Bo Liu, Kele Xu, Xinjun Mao, Huaimin Wang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Computer Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10908063/
Tags: Add Tag
No Tags, Be the first to tag this record!