Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning
Abstract
Non-exemplar class-incremental learning aims to recognize both the old and new classes without access to old class samples. The conflict between old and new class optimization is exacerbated since the shared neural pathways can only be differentiated by the incremental samples. To address this problem, we propose a novel self-organizing pathway expansion scheme. Our scheme consists of a class-specific pathway organization strategy that reduces the coupling of optimization pathway among different classes to enhance the independence of the feature representation, and a pathway-guided feature optimization mechanism to mitigate the update interference between the old and new classes. Extensive experiments on four datasets demonstrate significant performance gains, outperforming the state-of-the-art methods by a margin of 1%, 3%, 2% and 2%, respectively.
Cite
Text
Zhu et al. "Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning." International Conference on Computer Vision, 2023. doi:10.1109/ICCV51070.2023.01759Markdown
[Zhu et al. "Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning." International Conference on Computer Vision, 2023.](https://mlanthology.org/iccv/2023/zhu2023iccv-selforganizing/) doi:10.1109/ICCV51070.2023.01759BibTeX
@inproceedings{zhu2023iccv-selforganizing,
title = {{Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning}},
author = {Zhu, Kai and Zheng, Kecheng and Feng, Ruili and Zhao, Deli and Cao, Yang and Zha, Zheng-Jun},
booktitle = {International Conference on Computer Vision},
year = {2023},
pages = {19204-19213},
doi = {10.1109/ICCV51070.2023.01759},
url = {https://mlanthology.org/iccv/2023/zhu2023iccv-selforganizing/}
}