Open AccessMeshCut data augmentation for deep learning in computer vision
Author(s) -
Wei Jiang,
Kai Zhang,
Nan Wang,
Miao Yu
Publication year - 2020
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0243613
Subject(s) - overfitting , computer science , margin (machine learning) , convolutional neural network , artificial intelligence , machine learning , deep learning , variety (cybernetics) , baseline (sea) , artificial neural network , pattern recognition (psychology) , oceanography , geology
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.