Next Article in Journal
Acknowledgment to Reviewers of Technologies in 2020
Next Article in Special Issue
Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem
Previous Article in Journal
Intelligent System for Vehicles Number Plate Detection and Recognition Using Convolutional Neural Networks
Previous Article in Special Issue
A Survey of Robots in Healthcare

Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network

Department of Computer Science and Engineering, The University of Texas at Arlington (UTA), Arlington, TX 76019, USA
Author to whom correspondence should be addressed.
Academic Editors: Abdellah Chehri and Pedro Antonio Gutiérrez
Technologies 2021, 9(1), 10;
Received: 31 October 2020 / Revised: 10 January 2021 / Accepted: 15 January 2021 / Published: 21 January 2021
(This article belongs to the Collection Selected Papers from the PETRA Conference Series)
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. View Full-Text
Keywords: semisupervised learning; metric learning; signal recovery semisupervised learning; metric learning; signal recovery
Show Figures

Figure 1

MDPI and ACS Style

Banerjee, D.; Kyrarini, M.; Kim, W.H. Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network. Technologies 2021, 9, 10.

AMA Style

Banerjee D, Kyrarini M, Kim WH. Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network. Technologies. 2021; 9(1):10.

Chicago/Turabian Style

Banerjee, Debapriya, Maria Kyrarini, and Won H. Kim. 2021. "Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network" Technologies 9, no. 1: 10.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop