Diverse Data Selection Considering Data Distribution for Unsupervised Continual Learning

Naoto Hayashi, Naoki Okamoto, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

2024

Abstract

In continual learning, the train data changes during the learning process, making it difficult to solve previously learned tasks as the model adapts to the new task data. Many methods have been proposed to prevent catastrophic forgetting in continual learning. To overcome this problem, Lifelong Unsupervised Mixup (LUMP) has been proposed, which is capable of learning unlabeled data that can be acquired in the real world. LUMP trains a model by self-supervised learning method, and prevents catastrophic forgetting by using a mixup of a data augmentation method and a replay buffer that stores a part of the data used to train previous tasks. However, LUMP randomly selects data to store in the replay buffer from the train data, which may bias the stored data and cause the model to specialize in some data. Therefore, we propose a method for selecting data to be stored in the replay buffer for unsupervised continuous learning method.The proposed method splits the distribution of train data into multiple clusters using the k-means clustering. Next, one piece of data is selected from each cluster. The data selected by the proposed method preserves the distribution of the original data, making it more useful for self-supervised learning.

Paper Citation

in Harvard Style

Hayashi N., Okamoto N., Hirakawa T., Yamashita T. and Fujiyoshi H. (2024). Diverse Data Selection Considering Data Distribution for Unsupervised Continual Learning. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 528-535. DOI: 10.5220/0012369300003660

in Bibtex Style

@conference{visapp24,
author={Naoto Hayashi and Naoki Okamoto and Tsubasa Hirakawa and Takayoshi Yamashita and Hironobu Fujiyoshi},
title={Diverse Data Selection Considering Data Distribution for Unsupervised Continual Learning},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={528-535},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012369300003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Diverse Data Selection Considering Data Distribution for Unsupervised Continual Learning
SN - 978-989-758-679-8
AU - Hayashi N.
AU - Okamoto N.
AU - Hirakawa T.
AU - Yamashita T.
AU - Fujiyoshi H.
PY - 2024
SP - 528
EP - 535
DO - 10.5220/0012369300003660
PB - SciTePress