WEKO3
アイテム
Semi-supervised learning using VAE generated data and unlabeled data
https://ipsj.ixsq.nii.ac.jp/records/232333
https://ipsj.ixsq.nii.ac.jp/records/2323331f18dfe6-f06f-432a-b1bf-aa198d61ea7a
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-EIP24103006.pdf (3.1 MB)
2026年2月8日からダウンロード可能です。
|
Copyright (c) 2024 by the Information Processing Society of Japan
|
|
| 非会員：¥660, IPSJ:学会員：¥330, EIP:会員：¥0, DLIB:会員：¥0 | ||
| Item type | SIG Technical Reports(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-02-08 | |||||||||
| タイトル | ||||||||||
| タイトル | Semi-supervised learning using VAE generated data and unlabeled data | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Semi-supervised learning using VAE generated data and unlabeled data | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | 社会基盤(2) | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||||||
| 資源タイプ | technical report | |||||||||
| 著者所属 | ||||||||||
| Ryukyu University | ||||||||||
| 著者所属 | ||||||||||
| Ryukyu University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Ryukyu University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Ryukyu University | ||||||||||
| 著者名 |
Subin, Choi
× Subin, Choi
× Dongshik, Kang
|
|||||||||
| 著者名(英) |
Subin, Choi
× Subin, Choi
× Dongshik, Kang
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | This paper introduces a semi-supervised learning framework that employs Variational Autoencoders (VAEs) to create synthetic data, thereby enhancing the training sets in smart factory environments where labeled data is typically scarce. By accurately modeling the input data distribution, VAEs are able to generate new instances that closely resemble the real dataset, enriching the available data for model training. This strategy significantly reduces the need for laborious labeling efforts while improving the robustness of the datasets. The effectiveness of this approach is validated using the STL-10 and MNIST datasets. Results show a modest decrease in accuracy for the STL-10 dataset, dropping from 0.44 to 0.41 when incorporating VAE-augmented data into the training process. Similarly, the accuracy for the MNIST dataset slightly fell from 0.99 to 0.97 when applying the semi-supervised technique. These findings highlight the importance of precise calibration in the use of unlabeled data to ensure sustained model performance. Further investigation is suggested to enhance VAE configurations and the semi-supervised learning process, potentially improving the outcome of such methods. Additionally, the semi-supervised learning in this context employs the Mixmatch algorithm, which facilitates the effective integration of labeled and unlabeled data. Image classification tasks within the study are carried out using Convolutional Neural Networks (CNNs), capitalizing on their powerful feature extraction capabilities. Future research directions may include the refinement of Mixmatch parameters and CNN architectures to further leverage the composite dataset of VAE-generated and unlabeled data for optimal performance in image classification tasks. | |||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | This paper introduces a semi-supervised learning framework that employs Variational Autoencoders (VAEs) to create synthetic data, thereby enhancing the training sets in smart factory environments where labeled data is typically scarce. By accurately modeling the input data distribution, VAEs are able to generate new instances that closely resemble the real dataset, enriching the available data for model training. This strategy significantly reduces the need for laborious labeling efforts while improving the robustness of the datasets. The effectiveness of this approach is validated using the STL-10 and MNIST datasets. Results show a modest decrease in accuracy for the STL-10 dataset, dropping from 0.44 to 0.41 when incorporating VAE-augmented data into the training process. Similarly, the accuracy for the MNIST dataset slightly fell from 0.99 to 0.97 when applying the semi-supervised technique. These findings highlight the importance of precise calibration in the use of unlabeled data to ensure sustained model performance. Further investigation is suggested to enhance VAE configurations and the semi-supervised learning process, potentially improving the outcome of such methods. Additionally, the semi-supervised learning in this context employs the Mixmatch algorithm, which facilitates the effective integration of labeled and unlabeled data. Image classification tasks within the study are carried out using Convolutional Neural Networks (CNNs), capitalizing on their powerful feature extraction capabilities. Future research directions may include the refinement of Mixmatch parameters and CNN architectures to further leverage the composite dataset of VAE-generated and unlabeled data for optimal performance in image classification tasks. | |||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AA11238429 | |||||||||
| 書誌情報 |
研究報告電子化知的財産・社会基盤（EIP） 巻 2024-EIP-103, 号 6, p. 1-9, 発行日 2024-02-08 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 2188-8647 | |||||||||
| Notice | ||||||||||
| SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. | ||||||||||
| 出版者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
