دورية أكاديمية
ReliaMatch: Semi-Supervised Classification with Reliable Match
العنوان: | ReliaMatch: Semi-Supervised Classification with Reliable Match |
---|---|
المؤلفون: | Tao Jiang, Luyao Chen, Wanqing Chen, Wenjuan Meng, Peihan Qi |
المصدر: | Applied Sciences, Vol 13, Iss 15, p 8856 (2023) |
بيانات النشر: | MDPI AG, 2023. |
سنة النشر: | 2023 |
المجموعة: | LCC:Technology LCC:Engineering (General). Civil engineering (General) LCC:Biology (General) LCC:Physics LCC:Chemistry |
مصطلحات موضوعية: | deep learning, semi-supervised learning, pseudo labels, classification, ReliaMatch, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999 |
الوصف: | Deep learning has been widely used in various tasks such as computer vision, natural language processing, predictive analysis, and recommendation systems in the past decade. However, practical scenarios often lack labeled data, posing challenges for traditional supervised methods. Semi-supervised classification methods address this by leveraging both labeled and unlabeled data to enhance model performance, but they face challenges in effectively utilizing unlabeled data and distinguishing reliable information from unreliable sources. This paper introduced ReliaMatch, a semi-supervised classification method that addresses these challenges by using a confidence threshold. It incorporates a curriculum learning stage, feature filtering, and pseudo-label filtering to improve classification accuracy and reliability. The feature filtering module eliminates ambiguous semantic features by comparing labeled and unlabeled data in the feature space. The pseudo-label filtering module removes unreliable pseudo-labels with low confidence, enhancing algorithm reliability. ReliaMatch employs a curriculum learning training mode, gradually increasing training dataset difficulty by combining selected samples and pseudo-labels with labeled data. This supervised approach enhances classification performance. Experimental results show that ReliaMatch effectively overcomes challenges associated with the underutilization of unlabeled data and the introduction of error information, outperforming the pseudo-label strategy in semi-supervised classification. |
نوع الوثيقة: | article |
وصف الملف: | electronic resource |
اللغة: | English |
تدمد: | 13158856 2076-3417 |
Relation: | https://www.mdpi.com/2076-3417/13/15/8856; https://doaj.org/toc/2076-3417 |
DOI: | 10.3390/app13158856 |
URL الوصول: | https://doaj.org/article/d44f15329cc64a178ab7257451bfd854 |
رقم الأكسشن: | edsdoj.44f15329cc64a178ab7257451bfd854 |
قاعدة البيانات: | Directory of Open Access Journals |
تدمد: | 13158856 20763417 |
---|---|
DOI: | 10.3390/app13158856 |