Cargando…
MeshCut data augmentation for deep learning in computer vision
To solve overfitting in machine learning, we propose a novel data augmentation method called MeshCut, which uses a mesh-like mask to segment the whole image to achieve more partial diversified information. In our experiments, this strategy outperformed the existing augmentation strategies and achiev...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7757822/ https://www.ncbi.nlm.nih.gov/pubmed/33362231 http://dx.doi.org/10.1371/journal.pone.0243613 |
_version_ | 1783626806425812992 |
---|---|
author | Jiang, Wei Zhang, Kai Wang, Nan Yu, Miao |
author_facet | Jiang, Wei Zhang, Kai Wang, Nan Yu, Miao |
author_sort | Jiang, Wei |
collection | PubMed |
description | To solve overfitting in machine learning, we propose a novel data augmentation method called MeshCut, which uses a mesh-like mask to segment the whole image to achieve more partial diversified information. In our experiments, this strategy outperformed the existing augmentation strategies and achieved state-of-the-art results in a variety of computer vision tasks. MeshCut is also an easy-to-implement strategy that can efficiently improve the performance of the existing convolutional neural network models by a good margin without careful hand-tuning. The performance of such a strategy can be further improved by incorporating it into other augmentation strategies, which can make MeshCut a promising baseline strategy for future data augmentation algorithms. |
format | Online Article Text |
id | pubmed-7757822 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-77578222021-01-06 MeshCut data augmentation for deep learning in computer vision Jiang, Wei Zhang, Kai Wang, Nan Yu, Miao PLoS One Research Article To solve overfitting in machine learning, we propose a novel data augmentation method called MeshCut, which uses a mesh-like mask to segment the whole image to achieve more partial diversified information. In our experiments, this strategy outperformed the existing augmentation strategies and achieved state-of-the-art results in a variety of computer vision tasks. MeshCut is also an easy-to-implement strategy that can efficiently improve the performance of the existing convolutional neural network models by a good margin without careful hand-tuning. The performance of such a strategy can be further improved by incorporating it into other augmentation strategies, which can make MeshCut a promising baseline strategy for future data augmentation algorithms. Public Library of Science 2020-12-23 /pmc/articles/PMC7757822/ /pubmed/33362231 http://dx.doi.org/10.1371/journal.pone.0243613 Text en © 2020 Jiang et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Jiang, Wei Zhang, Kai Wang, Nan Yu, Miao MeshCut data augmentation for deep learning in computer vision |
title | MeshCut data augmentation for deep learning in computer vision |
title_full | MeshCut data augmentation for deep learning in computer vision |
title_fullStr | MeshCut data augmentation for deep learning in computer vision |
title_full_unstemmed | MeshCut data augmentation for deep learning in computer vision |
title_short | MeshCut data augmentation for deep learning in computer vision |
title_sort | meshcut data augmentation for deep learning in computer vision |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7757822/ https://www.ncbi.nlm.nih.gov/pubmed/33362231 http://dx.doi.org/10.1371/journal.pone.0243613 |
work_keys_str_mv | AT jiangwei meshcutdataaugmentationfordeeplearningincomputervision AT zhangkai meshcutdataaugmentationfordeeplearningincomputervision AT wangnan meshcutdataaugmentationfordeeplearningincomputervision AT yumiao meshcutdataaugmentationfordeeplearningincomputervision |