Deep Semi-Supervised Image Classification Algorithms: a Survey
Semi-supervised learning is a branch of machine learning focused on improving the performance of models when the labeled data is scarce, but there is access to large number of unlabeled examples. Over the past five years there has been a remarkable progress in designing algorithms which are able to...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Graz University of Technology
2021-12-01
|
| Series: | Journal of Universal Computer Science |
| Subjects: | |
| Online Access: | https://lib.jucs.org/article/77029/download/pdf/ |
| _version_ | 1819175404136562688 |
|---|---|
| author | Ani Vanyan Hrant Khachatrian |
| author_facet | Ani Vanyan Hrant Khachatrian |
| author_sort | Ani Vanyan |
| collection | DOAJ |
| description | Semi-supervised learning is a branch of machine learning focused on improving the performance of models when the labeled data is scarce, but there is access to large number of unlabeled examples. Over the past five years there has been a remarkable progress in designing algorithms which are able to get reasonable image classification accuracy having access to the labels for only 0.1% of the samples. In this survey, we describe most of the recently proposed deep semi-supervised learning algorithms for image classification and identify the main trends of research in the field. Next, we compare several components of the algorithms, discuss the challenges of reproducing the results in this area, and highlight recently proposed applications of the methods originally developed for semi-supervised learning. |
| first_indexed | 2024-12-22T20:54:19Z |
| format | Article |
| id | doaj.art-c6a935f5f7e14361bcc2f8db815a9b8e |
| institution | Directory Open Access Journal |
| issn | 0948-6968 |
| language | English |
| last_indexed | 2024-12-22T20:54:19Z |
| publishDate | 2021-12-01 |
| publisher | Graz University of Technology |
| record_format | Article |
| series | Journal of Universal Computer Science |
| spelling | doaj.art-c6a935f5f7e14361bcc2f8db815a9b8e2022-12-21T18:12:59ZengGraz University of TechnologyJournal of Universal Computer Science0948-69682021-12-0127121390140710.3897/jucs.7702977029Deep Semi-Supervised Image Classification Algorithms: a SurveyAni Vanyan0Hrant Khachatrian1YerevaNNYerevaNNSemi-supervised learning is a branch of machine learning focused on improving the performance of models when the labeled data is scarce, but there is access to large number of unlabeled examples. Over the past five years there has been a remarkable progress in designing algorithms which are able to get reasonable image classification accuracy having access to the labels for only 0.1% of the samples. In this survey, we describe most of the recently proposed deep semi-supervised learning algorithms for image classification and identify the main trends of research in the field. Next, we compare several components of the algorithms, discuss the challenges of reproducing the results in this area, and highlight recently proposed applications of the methods originally developed for semi-supervised learning.https://lib.jucs.org/article/77029/download/pdf/Machine learningSemi-supervised learningConsis |
| spellingShingle | Ani Vanyan Hrant Khachatrian Deep Semi-Supervised Image Classification Algorithms: a Survey Journal of Universal Computer Science Machine learning Semi-supervised learning Consis |
| title | Deep Semi-Supervised Image Classification Algorithms: a Survey |
| title_full | Deep Semi-Supervised Image Classification Algorithms: a Survey |
| title_fullStr | Deep Semi-Supervised Image Classification Algorithms: a Survey |
| title_full_unstemmed | Deep Semi-Supervised Image Classification Algorithms: a Survey |
| title_short | Deep Semi-Supervised Image Classification Algorithms: a Survey |
| title_sort | deep semi supervised image classification algorithms a survey |
| topic | Machine learning Semi-supervised learning Consis |
| url | https://lib.jucs.org/article/77029/download/pdf/ |
| work_keys_str_mv | AT anivanyan deepsemisupervisedimageclassificationalgorithmsasurvey AT hrantkhachatrian deepsemisupervisedimageclassificationalgorithmsasurvey |