Boostis:boosting image semi-supervised learning through pseudo-label quality assessment.
Saved in:
| Title: | Boostis:boosting image semi-supervised learning through pseudo-label quality assessment. |
|---|---|
| Authors: | Liu, Pingping1,2,3 (AUTHOR) liupp@jlu.edu.cn, Chen, Pengfei4 (AUTHOR) chenpf21@mails.jlu.edu.cn, Liu, Xiaofeng1 (AUTHOR) lxf22@mails.jlu.edu.cn, Zhou, Qiuzhan5 (AUTHOR) zhouqz@jlu.edu.cn |
| Source: | Pattern Analysis & Applications. Dec2025, Vol. 28 Issue 4, p1-13. 13p. |
| Abstract: | In recent years, significant progress has been made in semi-supervised learning methods that leverage pseudo-labels and consistency regularization. However, two key issues with existing approaches have been identified. Firstly, these methods often focus on maintaining inter-class consistency between strong and weak augmentations, but they tend to overlook intra-class differences. This oversight results in a waste of valuable intra-class information. Secondly, the selection of a fixed high threshold for pseudo-label confidence restricts the quantity and utilization of pseudo-labels. On the contrary, using an initial low threshold introduces a large number of erroneous pseudo-labels, resulting in a degradation of the model’s performance. To address these issues, we propose a novel semi-supervised learning framework that combines contrastive learning and feature discrepancy loss. Our approach introduces a new loss function that facilitates intra-class discrimination by emphasizing inter-class differences. Additionally, we tackle the threshold problem in pseudo-label consistency loss by introducing dynamic weighting coefficients. These coefficients help balance the impact of both the quantity and quality of pseudo-labels on the model. Our experimental results demonstrate that our method effectively harnesses the feature differences among samples with different perturbations. This enhancement boosts the model’s feature generation capability while mitigating the negative effects of erroneous pseudo-labels on model’s performance. Overall, our proposed framework provides a more comprehensive and effective solution to semi-supervised learning in classification applications by addressing the issues of intra-class differences and the selection of pseudo-label thresholds. [ABSTRACT FROM AUTHOR] |
| Copyright of Pattern Analysis & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 187657333 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Boostis:boosting image semi-supervised learning through pseudo-label quality assessment. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Liu%2C+Pingping%22">Liu, Pingping</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> liupp@jlu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Pengfei%22">Chen, Pengfei</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> chenpf21@mails.jlu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Xiaofeng%22">Liu, Xiaofeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lxf22@mails.jlu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Qiuzhan%22">Zhou, Qiuzhan</searchLink><relatesTo>5</relatesTo> (AUTHOR)<i> zhouqz@jlu.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Pattern+Analysis+%26+Applications%22">Pattern Analysis & Applications</searchLink>. Dec2025, Vol. 28 Issue 4, p1-13. 13p. – Name: Abstract Label: Abstract Group: Ab Data: In recent years, significant progress has been made in semi-supervised learning methods that leverage pseudo-labels and consistency regularization. However, two key issues with existing approaches have been identified. Firstly, these methods often focus on maintaining inter-class consistency between strong and weak augmentations, but they tend to overlook intra-class differences. This oversight results in a waste of valuable intra-class information. Secondly, the selection of a fixed high threshold for pseudo-label confidence restricts the quantity and utilization of pseudo-labels. On the contrary, using an initial low threshold introduces a large number of erroneous pseudo-labels, resulting in a degradation of the model’s performance. To address these issues, we propose a novel semi-supervised learning framework that combines contrastive learning and feature discrepancy loss. Our approach introduces a new loss function that facilitates intra-class discrimination by emphasizing inter-class differences. Additionally, we tackle the threshold problem in pseudo-label consistency loss by introducing dynamic weighting coefficients. These coefficients help balance the impact of both the quantity and quality of pseudo-labels on the model. Our experimental results demonstrate that our method effectively harnesses the feature differences among samples with different perturbations. This enhancement boosts the model’s feature generation capability while mitigating the negative effects of erroneous pseudo-labels on model’s performance. Overall, our proposed framework provides a more comprehensive and effective solution to semi-supervised learning in classification applications by addressing the issues of intra-class differences and the selection of pseudo-label thresholds. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Pattern Analysis & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=187657333 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10044-025-01537-3 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 1 Titles: – TitleFull: Boostis:boosting image semi-supervised learning through pseudo-label quality assessment. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Liu, Pingping – PersonEntity: Name: NameFull: Chen, Pengfei – PersonEntity: Name: NameFull: Liu, Xiaofeng – PersonEntity: Name: NameFull: Zhou, Qiuzhan IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 14337541 Numbering: – Type: volume Value: 28 – Type: issue Value: 4 Titles: – TitleFull: Pattern Analysis & Applications Type: main |
| ResultId | 1 |
