Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network
Weakly labeled data are inevitable in various research areas in artificial intelligence (AI) where one has a modicum of knowledge about the complete dataset. One of the reasons for weakly labeled data in AI is insufficient accurately labeled data. Strict privacy control or accidental loss may also c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/9/1/10 |
| _version_ | 1797408696901304320 |
|---|---|
| author | Debapriya Banerjee Maria Kyrarini Won Hwa Kim |
| author_facet | Debapriya Banerjee Maria Kyrarini Won Hwa Kim |
| author_sort | Debapriya Banerjee |
| collection | DOAJ |
| description | Weakly labeled data are inevitable in various research areas in artificial intelligence (AI) where one has a modicum of knowledge about the complete dataset. One of the reasons for weakly labeled data in AI is insufficient accurately labeled data. Strict privacy control or accidental loss may also cause missing-data problems. However, supervised machine learning (ML) requires accurately labeled data in order to successfully solve a problem. Data labeling is difficult and time-consuming as it requires manual work, perfect results, and sometimes human experts to be involved (e.g., medical labeled data). In contrast, unlabeled data are inexpensive and easily available. Due to there not being enough labeled training data, researchers sometimes only obtain one or few data points per category or label. Training a supervised ML model from the small set of labeled data is a challenging task. The objective of this research is to recover missing labels from the dataset using state-of-the-art ML techniques using a semisupervised ML approach. In this work, a novel convolutional neural network-based framework is trained with a few instances of a class to perform metric learning. The dataset is then converted into a graph signal, which is recovered using a recover algorithm (RA) in graph Fourier transform. The proposed approach was evaluated on a Fashion dataset for accuracy and precision and performed significantly better than graph neural networks and other state-of-the-art methods. |
| first_indexed | 2024-03-09T04:02:15Z |
| format | Article |
| id | doaj.art-2a5b0c314afb49a59fbfb6e04b243a7d |
| institution | Directory Open Access Journal |
| issn | 2227-7080 |
| language | English |
| last_indexed | 2024-03-09T04:02:15Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj.art-2a5b0c314afb49a59fbfb6e04b243a7d2023-12-03T14:11:12ZengMDPI AGTechnologies2227-70802021-01-01911010.3390/technologies9010010Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese NetworkDebapriya Banerjee0Maria Kyrarini1Won Hwa Kim2Department of Computer Science and Engineering, The University of Texas at Arlington (UTA), Arlington, TX 76019, USADepartment of Computer Science and Engineering, The University of Texas at Arlington (UTA), Arlington, TX 76019, USADepartment of Computer Science and Engineering, The University of Texas at Arlington (UTA), Arlington, TX 76019, USAWeakly labeled data are inevitable in various research areas in artificial intelligence (AI) where one has a modicum of knowledge about the complete dataset. One of the reasons for weakly labeled data in AI is insufficient accurately labeled data. Strict privacy control or accidental loss may also cause missing-data problems. However, supervised machine learning (ML) requires accurately labeled data in order to successfully solve a problem. Data labeling is difficult and time-consuming as it requires manual work, perfect results, and sometimes human experts to be involved (e.g., medical labeled data). In contrast, unlabeled data are inexpensive and easily available. Due to there not being enough labeled training data, researchers sometimes only obtain one or few data points per category or label. Training a supervised ML model from the small set of labeled data is a challenging task. The objective of this research is to recover missing labels from the dataset using state-of-the-art ML techniques using a semisupervised ML approach. In this work, a novel convolutional neural network-based framework is trained with a few instances of a class to perform metric learning. The dataset is then converted into a graph signal, which is recovered using a recover algorithm (RA) in graph Fourier transform. The proposed approach was evaluated on a Fashion dataset for accuracy and precision and performed significantly better than graph neural networks and other state-of-the-art methods.https://www.mdpi.com/2227-7080/9/1/10semisupervised learningmetric learningsignal recovery |
| spellingShingle | Debapriya Banerjee Maria Kyrarini Won Hwa Kim Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network Technologies semisupervised learning metric learning signal recovery |
| title | Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network |
| title_full | Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network |
| title_fullStr | Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network |
| title_full_unstemmed | Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network |
| title_short | Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network |
| title_sort | image label recovery on fashion data using image similarity from triple siamese network |
| topic | semisupervised learning metric learning signal recovery |
| url | https://www.mdpi.com/2227-7080/9/1/10 |
| work_keys_str_mv | AT debapriyabanerjee imagelabelrecoveryonfashiondatausingimagesimilarityfromtriplesiamesenetwork AT mariakyrarini imagelabelrecoveryonfashiondatausingimagesimilarityfromtriplesiamesenetwork AT wonhwakim imagelabelrecoveryonfashiondatausingimagesimilarityfromtriplesiamesenetwork |