Deep Metric Learning: A Survey
Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilize...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/9/1066 |
| _version_ | 1818000307829866496 |
|---|---|
| author | Mahmut Kaya Hasan Şakir Bilge |
| author_facet | Mahmut Kaya Hasan Şakir Bilge |
| author_sort | Mahmut Kaya |
| collection | DOAJ |
| description | Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods. |
| first_indexed | 2024-04-14T03:21:13Z |
| format | Article |
| id | doaj.art-bca5528022cd44aab58e6fff41fdcc2d |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-14T03:21:13Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-bca5528022cd44aab58e6fff41fdcc2d2022-12-22T02:15:19ZengMDPI AGSymmetry2073-89942019-08-01119106610.3390/sym11091066sym11091066Deep Metric Learning: A SurveyMahmut Kaya0Hasan Şakir Bilge1Department of Computer Engineering, Engineering Faculty, Siirt University, Siirt 56100, TurkeyDepartment of Electrical - Electronics Engineering, Engineering Faculty, Gazi University, Ankara 06570, TurkeyMetric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.https://www.mdpi.com/2073-8994/11/9/1066metric learningdeep metric learningsimilaritysiamese networktriplet network |
| spellingShingle | Mahmut Kaya Hasan Şakir Bilge Deep Metric Learning: A Survey Symmetry metric learning deep metric learning similarity siamese network triplet network |
| title | Deep Metric Learning: A Survey |
| title_full | Deep Metric Learning: A Survey |
| title_fullStr | Deep Metric Learning: A Survey |
| title_full_unstemmed | Deep Metric Learning: A Survey |
| title_short | Deep Metric Learning: A Survey |
| title_sort | deep metric learning a survey |
| topic | metric learning deep metric learning similarity siamese network triplet network |
| url | https://www.mdpi.com/2073-8994/11/9/1066 |
| work_keys_str_mv | AT mahmutkaya deepmetriclearningasurvey AT hasansakirbilge deepmetriclearningasurvey |