PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization

As artificial intelligence developed rapidly, deep learning models have been applied in various domains. While labeling is crucial to training models in fields that demand specific knowledge, producing such labeled datasets is expensive. Semi-supervised learning (SSL) is becoming a potential solutio...

Full description

Saved in:
Bibliographic Details
Main Authors: Mikyung Kang, Sooyon Seo, Moohong Min
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10918676/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041027088351232
author Mikyung Kang
Sooyon Seo
Moohong Min
author_facet Mikyung Kang
Sooyon Seo
Moohong Min
author_sort Mikyung Kang
collection DOAJ
description As artificial intelligence developed rapidly, deep learning models have been applied in various domains. While labeling is crucial to training models in fields that demand specific knowledge, producing such labeled datasets is expensive. Semi-supervised learning (SSL) is becoming a potential solution to this problem, utilizing data without label information. However, conventional SSL methods focus solely on predicting data classes while minimizing classification loss, which can lead to ambiguous decision boundaries, especially for classes with similar characteristics. In this study, we propose enhancing the baseline SSL method by incorporating a contrastive loss. We emphasize that samples near the decision boundaries have a negative impact on the model’s performance. Our method addresses the issue of uncertain boundaries in the representation space by focusing on the unique characteristics of each class. We conducted experiments to validate the effectiveness of our proposed method using a limited number of labeled samples. The results demonstrate that our method effectively enhances performance, particularly in environments with limited labeled data, as evidenced by visual analysis.
format Article
id doaj-art-2ff26cb699494e5dbb4a4a1871f868a7
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2ff26cb699494e5dbb4a4a1871f868a72025-08-20T02:55:53ZengIEEEIEEE Access2169-35362025-01-0113445434455410.1109/ACCESS.2025.354946510918676PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency RegularizationMikyung Kang0https://orcid.org/0000-0002-4412-3382Sooyon Seo1https://orcid.org/0009-0002-5595-6627Moohong Min2https://orcid.org/0000-0001-8979-1344Department of Applied Data Science, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Immersive Media Engineering, Sungkyunkwan University, Seoul, Republic of KoreaDepartment of Computer Education, Social Innovation Convergence Program, Sungkyunkwan University, Seoul, Republic of KoreaAs artificial intelligence developed rapidly, deep learning models have been applied in various domains. While labeling is crucial to training models in fields that demand specific knowledge, producing such labeled datasets is expensive. Semi-supervised learning (SSL) is becoming a potential solution to this problem, utilizing data without label information. However, conventional SSL methods focus solely on predicting data classes while minimizing classification loss, which can lead to ambiguous decision boundaries, especially for classes with similar characteristics. In this study, we propose enhancing the baseline SSL method by incorporating a contrastive loss. We emphasize that samples near the decision boundaries have a negative impact on the model’s performance. Our method addresses the issue of uncertain boundaries in the representation space by focusing on the unique characteristics of each class. We conducted experiments to validate the effectiveness of our proposed method using a limited number of labeled samples. The results demonstrate that our method effectively enhances performance, particularly in environments with limited labeled data, as evidenced by visual analysis.https://ieeexplore.ieee.org/document/10918676/Contrastive learningself-supervised learningsemi-supervised learning
spellingShingle Mikyung Kang
Sooyon Seo
Moohong Min
PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization
IEEE Access
Contrastive learning
self-supervised learning
semi-supervised learning
title PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization
title_full PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization
title_fullStr PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization
title_full_unstemmed PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization
title_short PC-Match: Semi-Supervised Learning With Progressive Contrastive and Consistency Regularization
title_sort pc match semi supervised learning with progressive contrastive and consistency regularization
topic Contrastive learning
self-supervised learning
semi-supervised learning
url https://ieeexplore.ieee.org/document/10918676/
work_keys_str_mv AT mikyungkang pcmatchsemisupervisedlearningwithprogressivecontrastiveandconsistencyregularization
AT sooyonseo pcmatchsemisupervisedlearningwithprogressivecontrastiveandconsistencyregularization
AT moohongmin pcmatchsemisupervisedlearningwithprogressivecontrastiveandconsistencyregularization