A model or 603 exemplars: Towards memory-efficient class-incremental learning

DW Zhou, QW Wang, HJ Ye, DC Zhan - arXiv preprint arXiv:2205.13218, 2022 - arxiv.org
Real-world applications require the classification model to adapt to new classes without
forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a …
被引用次数：90 相关文章

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

DW Zhou, QW Wang, HJ Ye, DC Zhan - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Real-world applications require the classification model to adapt to new classes without
forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a …

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

DW Zhou, QW Wang, HJ Ye, DC Zhan - The Eleventh International … - openreview.net
Real-world applications require the classification model to adapt to new classes without
forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a …
[PDF] researchgate.net

[PDF][PDF] AModel OR 603 EXEMPLARS: TOWARDS MEMORY-EFFICIENT CLASS-INCREMENTAL LEARNING

DW Zhou, QW Wang, HJ Ye, DC Zhan - researchgate.net
Real-world applications require the classification model to adapt to new classes without
forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a …