Preserving Linear Separability in Continual Learning by Backward Feature Projection-Reference-Cited by-同舟云学术

Preserving Linear Separability in Continual Learning by Backward Feature Projection

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Gu Qiao¹,Shim Dongsub²,Shkurti Florian¹

Affiliation:

1. University of Toronto

2. LG AI Research

Publisher

IEEE

Link

Reference51 articles.

1. Efficient lifelong learning with agem;chaudhry;ICLRE,2019

2. Riemannian walk for incremental learning: understanding forgetting and intransigence;chaudhry;ECCV,2018

4. Continual learning with tiny episodic memories;chaudhry;ICML,2019

5. Co21: Contrastive continual learning;cha;ICCV,2021

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Autonomous Generative Feature Replay for Non-Exemplar Class-Incremental Learning;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Improving Continual Relation Extraction with LSTM and Back Forward Projection;2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP);2023-12-15

4. Flashback for Continual Learning;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02