Cargando…
Tackling over-smoothing in multi-label image classification using graphical convolution neural network
The importance of the graphical convolution network in multi-label classification has grown in recent years due to its label embedding representation capabilities. The graphical convolution network is able to capture the label dependencies using the correlation between labels. However, the graphical...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9451128/ http://dx.doi.org/10.1007/s12530-022-09463-z |
_version_ | 1784784673141948416 |
---|---|
author | Chauhan, Vikas Tiwari, Aruna Venkata, Boppudi Naik, Vislavath |
author_facet | Chauhan, Vikas Tiwari, Aruna Venkata, Boppudi Naik, Vislavath |
author_sort | Chauhan, Vikas |
collection | PubMed |
description | The importance of the graphical convolution network in multi-label classification has grown in recent years due to its label embedding representation capabilities. The graphical convolution network is able to capture the label dependencies using the correlation between labels. However, the graphical convolution network suffers from an over-smoothing problem when the layers are increased in the network. Over-smoothing makes the nodes indistinguishable in the deep graphical convolution network. This paper proposes a normalization technique to tackle the over-smoothing problem in the graphical convolution network for multi-label classification. The proposed approach is an efficient multi-label object classifier based on a graphical convolution neural network that tackles the over-smoothing problem. The proposed approach normalizes the output of the graph such that the total pairwise squared distance between nodes remains the same after performing the convolution operation. The proposed approach outperforms the existing state-of-the-art approaches based on the results obtained from the experiments performed on MS-COCO and VOC2007 datasets. The experimentation results show that pairnorm mitigates the effect of over-smoothing in the case of using a deep graphical convolution network. |
format | Online Article Text |
id | pubmed-9451128 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-94511282022-09-07 Tackling over-smoothing in multi-label image classification using graphical convolution neural network Chauhan, Vikas Tiwari, Aruna Venkata, Boppudi Naik, Vislavath Evolving Systems Original Paper The importance of the graphical convolution network in multi-label classification has grown in recent years due to its label embedding representation capabilities. The graphical convolution network is able to capture the label dependencies using the correlation between labels. However, the graphical convolution network suffers from an over-smoothing problem when the layers are increased in the network. Over-smoothing makes the nodes indistinguishable in the deep graphical convolution network. This paper proposes a normalization technique to tackle the over-smoothing problem in the graphical convolution network for multi-label classification. The proposed approach is an efficient multi-label object classifier based on a graphical convolution neural network that tackles the over-smoothing problem. The proposed approach normalizes the output of the graph such that the total pairwise squared distance between nodes remains the same after performing the convolution operation. The proposed approach outperforms the existing state-of-the-art approaches based on the results obtained from the experiments performed on MS-COCO and VOC2007 datasets. The experimentation results show that pairnorm mitigates the effect of over-smoothing in the case of using a deep graphical convolution network. Springer Berlin Heidelberg 2022-09-07 /pmc/articles/PMC9451128/ http://dx.doi.org/10.1007/s12530-022-09463-z Text en © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022, Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Original Paper Chauhan, Vikas Tiwari, Aruna Venkata, Boppudi Naik, Vislavath Tackling over-smoothing in multi-label image classification using graphical convolution neural network |
title | Tackling over-smoothing in multi-label image classification using graphical convolution neural network |
title_full | Tackling over-smoothing in multi-label image classification using graphical convolution neural network |
title_fullStr | Tackling over-smoothing in multi-label image classification using graphical convolution neural network |
title_full_unstemmed | Tackling over-smoothing in multi-label image classification using graphical convolution neural network |
title_short | Tackling over-smoothing in multi-label image classification using graphical convolution neural network |
title_sort | tackling over-smoothing in multi-label image classification using graphical convolution neural network |
topic | Original Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9451128/ http://dx.doi.org/10.1007/s12530-022-09463-z |
work_keys_str_mv | AT chauhanvikas tacklingoversmoothinginmultilabelimageclassificationusinggraphicalconvolutionneuralnetwork AT tiwariaruna tacklingoversmoothinginmultilabelimageclassificationusinggraphicalconvolutionneuralnetwork AT venkataboppudi tacklingoversmoothinginmultilabelimageclassificationusinggraphicalconvolutionneuralnetwork AT naikvislavath tacklingoversmoothinginmultilabelimageclassificationusinggraphicalconvolutionneuralnetwork |