OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning
Abstract
In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions. Such misclassifications can degrade model performance. Techniques like open set recognition offer a means to detect these novel samples, representing a significant area in the machine learning domain.In this paper, we introduce a deep class-incremental learning framework integrated with open set recognition. Our approach refines class-incrementally learned features to adapt them for distance-based open set recognition. Experimental results validate that our method outperforms state-of-the-art incremental learning techniques and exhibits superior performance in open set recognition compared to baseline methods.
Cite
Text
Xu et al. "OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning." IEEE/CVF International Conference on Computer Vision Workshops, 2023. doi:10.1109/ICCVW60793.2023.00354Markdown
[Xu et al. "OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning." IEEE/CVF International Conference on Computer Vision Workshops, 2023.](https://mlanthology.org/iccvw/2023/xu2023iccvw-openincrement/) doi:10.1109/ICCVW60793.2023.00354BibTeX
@inproceedings{xu2023iccvw-openincrement,
title = {{OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning}},
author = {Xu, Jiawen and Grohnfeldt, Claas and Kao, Odej},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2023},
pages = {3295-3303},
doi = {10.1109/ICCVW60793.2023.00354},
url = {https://mlanthology.org/iccvw/2023/xu2023iccvw-openincrement/}
}